AI-generated summaries

Today's ML research,
without the noise.

Daily summaries of the latest machine learning papers from arXiv, processed every 8 hours.

67 Papers today
8h Update frequency
7 Days of history
Student Capacity Moderates Knowledge Distillation Effectiveness: A Systematic Study Across ResNet Teacher-Student Pairs on CIFAR-10
Umut Onur Yasar
Computer Vision Efficient ML Theory
  • Student capacity is a critical factor in the effectiveness of knowledge distillation.
  • Feature-KD can outperform Logit-KD when implemented correctly, contradicting previous assumptions.
  • Architectural adjustments for input resolution are essential for optimal performance in KD.
  • Implementation bugs can significantly skew the results of KD methods.
Read more
Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules
Nils Leutenegger
Computer Vision
  • Untrained neural networks often align better with early visual cortex than trained networks.
  • Supervised training, particularly with backpropagation, significantly degrades V1 alignment.
  • Different learning rules affect alignment dynamics differently, with BP being the most destructive.
  • Predictive coding and STDP preserve more brain-like structure compared to BP.
Read more
Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended
Aditya K Kamath, Arvind Krishnamurthy, Marco Canini, Simon Peter
Efficient ML Graph Learning Large Language Models
  • Introduces Invariant Bit Packing (IBP), a lossless compression algorithm tailored for ML workloads.
  • IBP achieves significant performance improvements, including 74% faster GNN training and 180% faster DLRM embedding lookup.
  • The method minimizes GPU memory usage while avoiding the accuracy trade-offs associated with lossy compression.
  • Provides easy-to-use APIs for integration into existing ML frameworks.
Read more
Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning
Yike Zhao, Onno Eberhard, Malek Khammassi, Ali H. Sayed, Michael Muehlebach
Reinforcement Learning Theory Efficient ML
  • Linear RNNs can effectively represent log-belief dynamics in partially observable environments.
  • The Adaptive Logit Filter (ALF) achieves optimal asymptotic error rates in state decoding.
  • The study establishes a connection between the eigenvalues of latent dynamics and environmental determinism.
  • The proposed filters highlight the representational efficiency of linear memories in RL.
Read more
When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception
Vahideh Zolfaghari
NLP Large Language Models Interpretability
  • Demonstrates that synthetic dishonesty can be rapidly induced in language models through supervised fine-tuning.
  • Linear representations of dishonesty are highly detectable, achieving near-perfect AUC in most models evaluated.
  • Probes trained on one domain (TruthfulQA) generalize effectively to diverse reasoning tasks (MMLU) with minimal performance loss.
  • Identifies two architectural regimes in models regarding their handling of dishonesty: collapse-type and high-dimensional models.
Read more
Apertus LLM Family Expansion via Distillation and Quantization
Andrei Panferov, Davit Melikidze, Martin Jaggi, Dan Alistarh
Large Language Models Efficient ML NLP
  • Introduction of the Apertus-v1.1 model family through distillation and quantization.
  • Demonstration of cost-effective model expansion without the need for extensive pre-training.
  • Validation of pre-training distillation as a method to enhance model performance with fewer resources.
  • Exploration of quantization techniques to optimize models for various hardware constraints.
Read more
Non-destructive Identification of Oyster Species is possible from Hyperspectral Images with Machine Learning
Ethan Kane Waters, Max Wingfield, Aiden Mellor, Paul Stewart, Iman Tahmasbian
Computer Vision
  • Hyperspectral imaging can non-destructively differentiate between oyster species.
  • PLS-DA outperformed CNN in classification accuracy for oyster species identification.
  • Distinct elemental compositions were found between Black-Lip and Sydney rock oysters.
  • The methodology has potential applications in aquaculture for species traceability and broodstock management.
Read more
The Sample Complexity of Multiclass and Sparse Contextual Bandits
Liad Erez, Fan Chen, Alon Cohen, Tomer Koren, Yishay Mansour, Shay Moran, Alexander Rakhlin
Theory Reinforcement Learning Efficient ML
  • Introduces improved sample complexity bounds for contextual bandits with sparse rewards.
  • Establishes algorithms that achieve ε-optimal policies with significantly reduced dependence on the number of actions.
  • Bridges a gap in existing literature by providing tight bounds that are minimax optimal up to logarithmic factors.
  • Utilizes two complementary approaches: DEC-based exploration and low-variance exploration techniques.
Read more
LoRe: Adaptive Interaction-Evaluation Routing with Per-Step Interaction Budgets for Iterative Graph Solvers
Jintao Li, Yong-Yi Wang, Zheng-An Wang, Heng Fan
Graph Learning Optimization Efficient ML
  • LoRe introduces a per-step operator budgeting framework for iterative graph solvers.
  • The method dynamically routes computation to high-conflict interactions, improving efficiency.
  • LoRe achieves a 15× speedup and 44× memory reduction on the TSP problem.
  • The framework is a drop-in solution that does not require retraining of existing models.
Read more
Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?
Marta Aparicio Rodriguez, Anastasia Borovykh, Grigorios A. Pavliotis, Daniel J. Korchinski
Generative Models
  • Diffusion models preferentially memorize common substrings over atypical samples.
  • Memorization behavior is influenced by dataset characteristics, particularly the presence of fat-tailed distributions.
  • An intermediate regime of partial memorization can lead to bland outputs, termed 'slop'.
  • Dataset diversity at higher abstraction levels is crucial for reducing memorization risks.
Read more
Solving Integer Linear Programming with Parallel Tempering
Kyuil Sim, Sanghyeok Choi, Jinkyoo Park
Optimization
  • Introduces a solver-free, sampling-based approach for ILP optimization.
  • Utilizes Locally-Balanced Proposal and Parallel Tempering to explore discrete feasible regions.
  • Demonstrates superior performance compared to SCIP and competitive results against Gurobi.
  • Shows robustness to distribution shifts compared to learning-based methods.
Read more
Augmented Lagrangian Predictive Coding
Jeffrey Seely, Julian Gould
Optimization Theory
  • PC-ALM integrates augmented Lagrangian methods into predictive coding to enhance local learning dynamics.
  • The method achieves BP-equivalent performance in nonlinear networks, particularly in deep narrow architectures.
  • PC-ALM introduces recurrent dynamics that facilitate faster and more uniform credit propagation across layers.
  • The approach maintains a finite inference budget while aligning weight updates with BP gradients.
Read more
Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
Konstantin Nikolaou, Jonas Scheunemann, Sven Krippendorf, Samuel Tovey, Christian Holm
Theory Optimization
  • Introduction of spectral position as a scalable measure of eigenvalue contributions to loss reduction.
  • Larger models achieve lower losses by accessing weak spectral signals in the eNTK spectrum.
  • Feature learning is identified as a key enabler of spectral reach, amplifying gradients during training.
  • The study provides a framework for understanding the dynamics of scaling in large-scale neural networks.
Read more
Spectral Anatomy of Quantum Gaussian Process Kernels
Jian Xu, Chao Li, Guang Lin, Yuning Qiu, Delu Zeng, John Paisley, Qibin Zhao
Theory Optimization
  • Introduces normalized spectral entropy as a key diagnostic for QGP kernels.
  • Establishes a connection between spectral properties and the performance of QGPs in Bayesian optimization.
  • Identifies a 'Goldilocks region' for kernel design that balances expressiveness and informativeness.
  • Demonstrates empirical validation of findings on quantum hardware with minimal error.
Read more
Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language Models
Heqiang Qi, Wei Huang, Mingyuan Bai, Xiangming Meng
NLP Large Language Models Generative Models
  • Introduction of confidence-induced clusters (CICs) as span-level update units for MDLMs.
  • Development of CLAD, a training-free cluster-level decoder that enhances parallel decoding.
  • Utilization of self-attention maps to model inter-cluster dependencies and ensure compatibility.
  • Demonstrated significant speed improvements over existing token-level decoding methods.
Read more
The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction
Shu Wan, Abhinav Gorantla, Huan Liu, K. Selçuk Candan
Theory Graph Learning Efficient ML
  • Restricting regressors to the Markov boundary can improve prediction, especially in larger and sparser feature spaces.
  • Causal discovery methods often fail to provide a useful boundary for prediction due to computational constraints and misalignment of objectives.
  • The exact Markov boundary is not the only effective feature set; alternative sets can also yield better performance than using all features.
  • The study highlights the trade-offs between minimality, sufficiency, and scalability in feature selection for tabular prediction.
Read more
Multivariate Distributional Reinforcement Learning Using Sliced Divergences
Baptiste Debes, Tinne Tuytelaars
Reinforcement Learning Theory
  • Introduction of Sliced Distributional Reinforcement Learning (SDRL) for multivariate return distributions.
  • Establishment of Bellman contraction under shared scalar discounting and a maximum-slicing variant for dense discount matrices.
  • Analysis of various base divergences suitable for SDRL, including Wasserstein and MMD.
  • Evaluation of SDRL on multiple environments, showcasing its practical applicability.
Read more
Evolutionary Refinement of Generative Graph Topologies: A Hybrid WGAN-GA Approach
James Sargant, Seyedeh Ava Razi Razavi, Renata Dividino, Sheridan Houghten
Generative Models Graph Learning Optimization
  • Combines WGANs with Genetic Algorithms for graph generation refinement.
  • Addresses structural deviations in generated graphs compared to real data.
  • Implements evolutionary edge editing to optimize graph connectivity.
  • Demonstrates improved alignment with real graph statistical properties.
Read more
The Hamilton-Jacobi Theory of Deep Learning
Jose Marie Antonio Miñoza, Erika Fille T. Legara, Christopher P. Monterola
Theory Optimization Interpretability
  • Training neural networks corresponds to solving Hamilton-Jacobi initial-value problems.
  • Log-sum-exp activation functions are smooth deformations of tropical max operations.
  • A single parameter ε connects various perspectives on neural networks, including tropical algebra and PDEs.
  • The framework provides actionable design principles for optimizing neural network architectures.
Read more
Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design
Sven Gutjahr, Riccardo De Santi, Luca Schaufelberger, Kjell Jorner, Andreas Krause
Generative Models Optimization
  • Introduction of a formal framework for Constrained Generative Optimization.
  • Development of the Constrained Flow Optimization (CFO) algorithm for balancing reward maximization and constraint satisfaction.
  • CFO provides convergence guarantees for constrained generative optimization.
  • Experimental results show consistent improvements in reward and constraint satisfaction.
Read more
CalArena: A Large-Scale Post-Hoc Calibration Benchmark
Eugène Berta, David Holzmüller, Francis Bach, Michael I. Jordan
Computer Vision Theory Optimization
  • Introduction of a large-scale benchmark for post-hoc calibration covering diverse tasks and models.
  • Standardized evaluation framework for comparing dozens of calibration methods.
  • Post-Hoc Improvement (PHI) proposed as a new metric for assessing calibration quality.
  • Empirical results show that smooth calibration functions are superior to binning methods.
Read more
Early Prediction of Future Behavioral Strategy from Process Traces
Robert Kasumba, Dennis Barbour, Chien-Ju Ho
Reinforcement Learning Time Series Robotics
  • The paper formulates early cross-task behavioral strategy prediction as a relevant problem.
  • Introduction of the Process-Level Latent Variable Model (PLVM) for fusing task-specific traces.
  • PLVM outperforms traditional outcome-based models and single-task models in predicting behavior.
  • Controlled simulations validate the effectiveness of PLVM in recovering behavioral phenotypes.
Read more
Momentum Based Reward Design for Low Emission Traffic Signal Control
Chinmay Mundane, Amith Manoharan, Arun Singh
Reinforcement Learning Optimization
  • Introduction of a Momentum-Based Reward Function (MBRF) that promotes continuous vehicle movement.
  • Evaluation of the MBRF in SUMO shows better performance than traditional delay and queue-based rewards.
  • The proposed method leads to improved throughput-emission trade-offs and more stable learning behaviors.
  • Demonstrates the effectiveness of DRL in adaptive traffic signal control without requiring major infrastructure changes.
Read more
CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment
Silas Ruhrberg Estévez, Nicolas Huynh, Tennison Liu, Roderik M. Kortlever, Gerard I. Evan, David L. Bentley, Mihaela van der Schaar
Graph Learning Time Series Interpretability
  • CellBRIDGE augments Optimal Transport with interaction-aware costs derived from ligand-receptor signaling.
  • The method improves trajectory inference by explicitly modeling cell-cell communication.
  • CellBRIDGE enables interpretable in silico perturbations that align with expected biological outcomes.
  • The approach shows broad applicability across various trajectory inference frameworks.
Read more
AMNESIA: A Large Scale Medical Unlearning Benchmark Suite with Disease-Informed Analysis
Saeedeh Davoudi, Reihaneh Iranmanesh, Ophir Frieder, Nazli Goharian
NLP Large Language Models Multimodal
  • AMNESIA is the first large-scale, clinically-grounded benchmark for medical unlearning.
  • The dataset includes 70,560 question-answer pairs from real patient notes across 11 disease categories.
  • The benchmark supports both factual and reasoning questions, enabling diverse evaluation scenarios.
  • Four unlearning methods were evaluated, revealing significant challenges in maintaining knowledge integrity.
Read more
Test Time Training for Supervised Causal Learning
Zizhen Deng, Jiaru Zhang, Rui Ding, Huang Bojun, Jinzhuo Wang, Qiang Fu, Shi Han, Dongmei Zhang
Graph Learning Theory Efficient ML
  • Identifies critical limitations in existing Supervised Causal Learning methods.
  • Introduces TTT-SCL, a framework for dynamic training set generation at test time.
  • Establishes a theoretical basis connecting TTT-SCL with score-based methods.
  • Demonstrates significant performance improvements across various datasets.
Read more
Fixed Universal Transformers
Jingwen Liu, Alexandr Andoni, Daniel Hsu
Theory
  • Introduces the notion of universal transformers that can simulate any transformer via input embeddings.
  • Provides explicit constructions for universal transformers and shows that randomly initialized transformers are universal.
  • Establishes lower bounds on the embedding dimensions required for universality in transformers with multiple heads.
  • Empirical evaluations demonstrate high accuracy in specific algorithmic tasks, supporting the theoretical findings.
Read more
UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
Yi Liu, Hongji Zhang, Lei Chen, Mingxuan Yuan, Qiang Xu
Multimodal Graph Learning
  • UniRTL integrates RTL code and CDFG for enhanced representation learning.
  • The framework employs mutual masked modeling for fine-grained cross-modal alignment.
  • A hierarchical training strategy is utilized to maximize data utilization.
  • UniRTL outperforms existing methods in performance prediction and code retrieval tasks.
Read more
Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects
Artur Szałata, Olga Novitskaia, Maiia Shulman, Matthew Mella, Altynbek Zhubanchaliyev, Fabian J. Theis
Theory
  • Chem-PerturBridge harmonizes diverse transcriptomic datasets, providing a unified resource for small-molecule perturbation modeling.
  • The resource includes over 37,000 compounds and 1.25 million transcriptomic samples, standardized for better usability.
  • Fine-grained logFC agreement across datasets is weak, while logFC direction agreement is more consistent.
  • Pretraining on Chem-PerturBridge significantly improves compound representation learning outcomes.
Read more
Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens
Junbin Qiu, Zhaowei Hong, Renzhe Xu, Yao Shu
Optimization Theory Efficient ML
  • Introduces a unified framework for ZO Hessian approximation using single-step Policy Optimization.
  • Presents ZoVH, a comprehensive suite of variance-reduced Hessian estimators.
  • Establishes theoretical guarantees for the unbiasedness and variance optimality of the proposed methods.
  • Demonstrates significant improvements in estimation accuracy and convergence performance in empirical evaluations.
Read more
CSULoRA: Closest Safe Update Low-Rank Adaptation
Oleksandr Marchenko Breneur, Adelaide Danilov, Aria Nourbakhsh, Salima Lamsiyah
NLP Large Language Models Efficient ML
  • CSULoRA is a post-hoc method that enhances safety in low-rank adaptation without retraining the model.
  • It decomposes LoRA updates into components based on their alignment with a safety-aligned subspace.
  • The method preserves task-relevant information while mitigating unsafe updates.
  • Experimental results show a significant reduction in attack success rates while retaining utility improvements.
Read more
Causal Intelligence for Constraint-Aware Intervention Design to Induce State Transitions
Zixuan Song, Uwe Mueller, Dimitris V. Manatakis
Optimization Graph Learning Interpretability
  • COAST provides a principled framework for designing interventions that induce state transitions in complex systems.
  • The framework integrates causal discovery and multi-objective optimization to balance efficacy, complexity, and stability of interventions.
  • COAST is modular and domain-agnostic, making it applicable across various fields, particularly in biomedicine.
  • The approach successfully identifies causal drivers and robust intervention strategies from both synthetic and real datasets.
Read more
Active Timepoint Selection for Learning Measure-Valued Trajectories
Nicolas Huynh, Mihaela van der Schaar
Time Series Optimization Theory
  • Introduces a framework for active timepoint selection in measure-valued trajectories.
  • Utilizes Linearized Optimal Transport to facilitate Gaussian Process modeling in non-Euclidean spaces.
  • Addresses the challenge of epistemic uncertainty quantification in distributional interpolation.
  • Empirical results show improved performance over uniform and random baselines.
Read more
IRIS: time-structured manifold projections
Brian Ondov, Chia-Hsuan Chang, Weipeng Zhou, Xingjian Zhang, Xueqing Peng, Yutong Xie, Huan He, Qiaozhu Mei, Hua Xu
Time Series Optimization Theory
  • IRIS integrates time-structured layouts with manifold learning, enhancing the visualization of dynamic biomedical data.
  • The algorithm operates in two phases: optimizing radial distances for timestamps and adjusting angular positions for high-dimensional structure.
  • Evaluation across multiple datasets shows IRIS outperforms UMAP in representing temporal relationships while retaining class structure.
  • The method is open-source, promoting accessibility and further research in the field.
Read more
Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting
Amirhossein Ghaffari, Saeid Sheikhi, Ekaterina Gilman
Graph Learning Time Series
  • GC-MoE utilizes a dual-pathway routing mechanism that combines static topology features with dynamic traffic input signals.
  • The framework allows for expert specialization by assigning different experts to different nodes based on their unique traffic patterns.
  • GC-MoE achieves significant improvements in forecasting accuracy while maintaining a low parameter count.
  • The optional output refinement layer can enhance performance further without substantial additional costs.
Read more
When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
Stephane Hatgis-Kessell, Emma Brunskill
Reinforcement Learning Large Language Models Robotics
  • Prompted Policy Optimization (PromptPO) leverages LLMs to optimize policies for RL tasks.
  • PromptPO often outperforms standard RL algorithms in terms of performance and sample efficiency.
  • The method generates a diverse range of policies based on the provided context.
  • LLMs may struggle with tasks requiring fine-grained control, indicating limitations in certain environments.
Read more
Generalized Intention Modeling in Multi-Agent Reinforcement Learning
Mateusz Odrowaz-Sypniewski, Jasmine Bayrooti, Ajay Shankar, Amanda Prorok
Reinforcement Learning
  • Introduction of a task-adaptive opponent modeling framework that combines multiple intent representations.
  • Development of reward-predictive intention embeddings that enhance the ego-agent's understanding of opponent impact on returns.
  • Demonstration of improved performance stability and robustness compared to traditional single-component modeling methods.
  • Insights into the varying effectiveness of opponent modeling strategies across different environments.
Read more
SigmaMedStat: Temporal Signal Modeling for ICU False Alarm Reduction
Arunkumar Ramachandran
Time Series
  • Introduces a novel temporal CWT-LSTM architecture for ICU alarm classification.
  • Achieves a mean AUC of 0.822, significantly outperforming static classification methods.
  • Demonstrates the importance of temporal chunking and multi-channel signal fusion.
  • Identifies specific alarm types that are easier or harder to classify.
Read more
Bridging Chemists and AI: An Expert-Augmented Framework for Interpretable Route Evaluation
Yujia Guo, Mikhail Kabeshov, Tat Hong Duong Le, Samuel Genheden, Marco V. Mijangos, Varvara Voinarvoska, Giulia Bergonzini, Ola Engkvist, Samuel Kaski
Interpretability
  • Introduces an expert-augmented framework combining machine learning with chemists' expertise for route evaluation.
  • Utilizes a DeepSets-based model trained on tree edit distances and fine-tuned with expert evaluations.
  • Achieves significant improvements in scoring accuracy and interpretability compared to existing methods.
  • Provides a dual-output evaluation system that aligns with real-world decision-making in synthesis planning.
Read more
Self-Certifying Transport MCMC via Dual Spectral-Gap Certificates
Jun Hu
Theory Generative Models Efficient ML
  • Introduction of CerT-MCMC framework for learned-transport MCMC with convergence certificates.
  • Development of two complementary certificates: covering certificate and quantile-core certificate.
  • Quantile-core certificate provides non-vacuous spectral-gap bounds in high dimensions.
  • Demonstrated effectiveness on various datasets, including synthetic and real-world applications.
Read more
Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints
Shervin Khalafi, Alejandro Ribeiro, Dongsheng Ding
Generative Models Optimization Theory
  • Introduces a principled constrained optimization framework for unlearning in diffusion models.
  • Formulates three optimization problems based on KL divergences and likelihood constraints.
  • Establishes strong duality for the proposed problems, enabling effective solution characterization.
  • Demonstrates superior performance of KL-constrained methods over traditional weight-based approaches.
Read more
Automating Formal Verification with Reinforcement Learning and Recursive Inference
Max Tan
Reinforcement Learning Large Language Models Theory
  • Introduces RLVR to improve formal verification in LLMs.
  • Achieves a verified reward increase from 2.2% to 58.1% using RLVR.
  • Identifies and addresses specification hacking in model outputs.
  • Develops a verifier-guided inference scaffold that improves proof generation success rates.
Read more
De-attribute to Forget for LLM Unlearning
Xinyang Lu, Jiabao Pan, Rachael Hwee Ling Sim, See-Kiong Ng, Anthony Kum Hoe Tung, Bryan Kian Hsiang Low
NLP Large Language Models Reinforcement Learning
  • Introduces a novel data de-attribution objective for LLM unlearning.
  • Presents DareU, the first LLM unlearning framework utilizing reinforcement learning.
  • Demonstrates effective unlearning while preserving model utility.
  • Outperforms existing LLM unlearning methods in empirical evaluations.
Read more
Improving Relative Representations with Learned Anchors and Whitened Inner Products
Oscar Thorsted Svendsen, Nikolaj Holst Jakobsen, Fabian Mager, Hiba Nassar
Multimodal
  • Introduces learned anchors as robust semantic prototypes for improved relative representations.
  • Utilizes a geometry-aware similarity metric that preserves magnitude information and is invariant to affine transformations.
  • Demonstrates significant performance gains in cross-model communication across vision and language tasks.
  • Enables stable zero-shot communication between models of varying scales and architectures.
Read more
OISD: On-Policy Internal Self-Distillation of Language Models
Xinyu Liu, Darryl Cherian Jacob, Yang Zhou, Jindong Wang, Pan He
NLP Large Language Models Reinforcement Learning
  • Introduction of On-Policy Internal Self-Distillation (OISD) for language models.
  • Utilizes the final layer as an internal teacher to guide intermediate layers.
  • Employs logit and attention alignment mechanisms for effective knowledge transfer.
  • Demonstrates substantial improvements in reasoning tasks over strong RL baselines.
Read more
MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment
Dang Hong Nguyen, Nhi Ngoc-Yen Nguyen, Huy-Hieu Pham
NLP Efficient ML Optimization
  • Introduction of MIC framework for optimizing multi-granular embeddings.
  • Development of Soft Collapse Regularization to manage redundancy in nested subspaces.
  • Implementation of Spectral Isotropy Regularization for ensuring uniformity in embeddings.
  • Demonstrated significant performance improvements over existing MRL baselines.
Read more
Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
Jabin Koo, Hoyoung Kim, Minwoo Jang, Jungseul Ok
Federated Learning Reinforcement Learning Large Language Models
  • Introduces FedVPA-GP to address limitations of monolithic reward models in federated learning.
  • Utilizes a Federated Mixture Prior to stabilize variational inference and prevent posterior collapse.
  • Incorporates Orthogonal Loss to ensure semantic separation of conflicting preference prototypes.
  • Demonstrates significant performance improvements over traditional methods on the HH-RLHF dataset.
Read more
RL2ML: Finite-Rollout Surrogate Objectives from Reinforcement Learning to Maximum Likelihood
Yifu Zheng
Reinforcement Learning NLP Large Language Models
  • RL2ML connects standard reinforcement learning, maximum-likelihood training, and beyond-maximum-likelihood objectives.
  • Introduces a closed-form unbiased gradient estimator for finite-rollout surrogate objectives.
  • Identifies a subcritical-supercritical update-scale transition that influences the effectiveness of surrogate objectives.
  • Demonstrates that the optimal choice of surrogate objective depends on evaluation metrics, local sensitivity, and estimator variance.
Read more
TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery
Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang, Han-Jia Ye
Graph Learning
  • TabCausal addresses the limitations of existing CDFMs by utilizing a broad causal pretraining framework.
  • The model can perform one-pass dataset-to-graph inference, enhancing efficiency in causal discovery.
  • Dynamic task construction enables learning from a wide range of causal environments, improving transferability.
  • TabCausal outperforms classical and neural causal discovery methods on synthetic and semantic benchmarks.
Read more
How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions
Jeff A. Bilmes, Gantavya Bhatt, Arnav M. Das
Theory Optimization Efficient ML
  • Dataset value is influenced by factors beyond size and compute budget.
  • The Vendi Score and neural scaling laws are shown to be submodular.
  • Matrix spectral functions provide a broader framework for dataset appraisal.
  • A new optimization method yields a 35,000× speedup for maximizing the Vendi Score.
Read more
On Distributional Reinforcement Learning in Chaotic Dynamical Systems
James Rudd-Jones, Mirco Musolesi, María Pérez-Ortiz
Reinforcement Learning Theory Optimization
  • Distributional RL objectives are smoother than expectation-based objectives in chaotic systems.
  • Return distributions under mild statistical stability assumptions are Lipschitz continuous in the 1-Wasserstein metric.
  • Empirical analysis shows that distributional objectives lead to smoother loss landscapes and lower variance targets.
  • Distributional Q-learning methods outperform non-distributional approaches in chaotic control experiments.
Read more
Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
Ruoran Xu, Borong She, Xiaobo Jin, Qiufeng Wang
Optimization Theory
  • Introduction of Singularity-aware Adam (S-Adam) to address issues in non-smooth optimization.
  • Development of the Local Geometric Instability (LGI) metric for estimating instability in loss landscapes.
  • Adaptive damping mechanism that modulates step sizes based on local geometric conditions.
  • Rigorous convergence guarantees established through differential inclusions.
Read more
Bifurcated Remaining Useful Life Prediction: A Hybrid Approach for Realistic Uncertainty Characterization
Xabier Belaunzaran, Antonio Nappa, Arkaitz Artetxe, Basilio Sierra
Time Series
  • Introduces a hybrid prognostic framework for RUL estimation that incorporates uncertainty quantification.
  • Utilizes a bifurcated approach to classify engine states into healthy and degraded regimes.
  • Employs an LSTM-based autoencoder for state classification and a Conditional Weibull model for RUL estimation.
  • Generates continuous state probabilities for improved prediction accuracy and uncertainty characterization.
Read more
MAAT: Multi-phase Adapter-Aware Targeted Unlearning
Suryash Yagnik, Shubham Gaur, Saksham Thakur, Vinija Jain, Aman Chadha, Amitava Das
NLP Large Language Models Theory
  • Introduction of 5WBENCH, a benchmark that quantifies causal unlearning failures.
  • MAAT framework achieves high forgetting and retention of Why-type causal knowledge.
  • Demonstrates the challenges of gradient dilution and multi-hop reasoning in unlearning.
  • Outperforms existing methods on the forget-retain tradeoff across multiple models.
Read more
Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
Santanu Das, Sagnik Chatterjee, Jatin Batra
Theory Efficient ML Optimization
  • Introduces a robust recovery algorithm for Gaussian Single Index Models with non-monotonic link functions.
  • Establishes the existence of a convex basin in the loss landscape that aids in robust recovery.
  • Demonstrates efficient convergence to low estimation error under adversarial conditions.
  • Fills a significant gap in robust statistics literature for non-monotonic link functions.
Read more
How's it going? Reinforcement learning in language models recruits a functional welfare axis
Andy Q Han, David J. Chalmers, Pavel Izmailov
NLP Large Language Models Reinforcement Learning
  • Reinforcement learning recruits a pre-existing representation of functional welfare in language models.
  • The study demonstrates that punishment and reward vectors behave as representations of negative and positive welfare, respectively.
  • The effects of these vectors are robust across various training conditions and persist even in pre-trained models.
  • The functional welfare axis influences model behavior in unrelated domains, indicating a generalization of learned representations.
Read more
ScaleMAP: Preserving Local Density and Neighborhood Structure in Low-Dimensional Embeddings
Rajas Poorna, Marcus T. Cicerone
Graph Learning Theory Efficient ML
  • ScaleMAP preserves local density and neighborhood structure better than existing methods.
  • It introduces a change of variables approach to reintroduce scale information in embeddings.
  • ScaleMAP matches DensMAP on density preservation while maintaining UMAP-level neighborhood preservation.
  • The method successfully recovers critical structures in various scientific datasets.
Read more
Towards Continuous-time Causal Foundation Models
Dennis Thumm, Ruben Wiedemann, Ying Chen
Time Series
  • Introduces a continuity criterion for continuous-time causal priors based on trajectory-law invariance.
  • Develops a three-tier taxonomy for categorizing causal priors in time series analysis.
  • Demonstrates that fine-grid integration outperforms naive integration in empirical tests.
  • Proposes a construction for continuous-time causal models using OU processes and random DAGs.
Read more
PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation
Junru Zhang, Lang Feng, Jinbo Wang, Xu Guo, Yucheng Wang, Han Yu, Min Wu, Yabo Dong, Duanqing Xu
Generative Models Time Series
  • PrismFlow addresses mode collapse in time-series generation by using a bank of Koopman-inspired experts.
  • The method employs a Winner-Take-All training objective to promote expert specialization and reduce averaging effects.
  • PrismFlow achieves state-of-the-art performance with significant improvements in key evaluation metrics.
  • The approach is robust in low-data settings and effective for various time-series tasks, including forecasting and imputation.
Read more
FlagGAM: Rule-Based Generalized Additive Modeling for Explainable Tabular Prediction
Zijie Zhao, Roy E. Welsch
Interpretability
  • FlagGAM provides a rule-defined basis framework for GAM-style tabular prediction.
  • It extends rule construction to handle both numerical and categorical features across classification and regression tasks.
  • The framework retains a sparse rule-basis matrix, allowing for feature-specific weighting and flexible prediction heads.
  • FlagGAM demonstrates competitive performance against modern additive models and tree-based methods, especially under challenging data conditions.
Read more
Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing
Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen
NLP Large Language Models Efficient ML
  • Introduces a unified framework for causal linear token mixing that generalizes existing architectures.
  • Explores the trade-offs between computational complexity and expressive power in token mixers.
  • Constructs token mixers with varying complexities, enhancing expressivity while managing runtime.
  • Empirical validation on synthetic benchmarks and language modeling tasks supports theoretical claims.
Read more
Retriever Portfolios: A Principled Approach to Adaptive RAG
Miltiadis Stouras, Vincent Cohen-Addad, Silvio Lattanzi, Ola Svensson
NLP Large Language Models Optimization
  • Introduces retriever portfolio optimization to enhance RAG systems by selecting diverse retrievers for heterogeneous queries.
  • Formalizes an expected best-of-k objective to evaluate retriever portfolios, ensuring coverage of different query types.
  • Demonstrates that fixed portfolios can achieve comparable or better accuracy with lower latency than adaptive hyperparameter tuning methods.
  • Empirical results show significant improvements in retrieval recall and answer accuracy across multiple QA benchmarks.
Read more
Scaling Higher-Order Graph Learning with Maximal Clique Complexes
Antoine Vialle, Aref Einizade, Fragkiskos D. Malliaros, Jhony H. Giraldo
Graph Learning
  • Introduction of sCWL and fCWL tests that preserve expressivity while improving scalability.
  • Development of the maximal clique complex for efficient higher-order graph representation.
  • CliqueWalk method for sampling maximal cliques, enabling linear scaling with graph size.
  • Competitive performance on classification benchmarks compared to existing GNNs.
Read more
The Long-Term Effects of Data Selection in LLM Fine-Tuning
Yuxin Yang, Aoxiong Zeng, Xiangquan Yang
NLP Large Language Models Theory
  • Introduces the concept of myopic selection in LLM fine-tuning, highlighting the trade-off between short-term gains and long-term adaptability.
  • Develops a unified multi-stage evaluation protocol for comparing various data selection strategies.
  • Demonstrates through experiments that short-term effective selectors can hinder future learning and increase forgetting.
  • Proposes the Long-Horizon Aware Selection (LHAS) objective to improve long-term adaptation and robustness.
Read more
Fraud Type Decomposition and the Observation-Mechanism Taxonomy: Class-Specific Detection Limits in Payment Networks
Gaurav Dhama
Theory
  • Fraud detection models often treat diverse fraud types as a single entity, leading to statistical inefficiencies.
  • The paper identifies five distinct observation-mechanism classes for fraud types, each requiring specific estimation strategies.
  • Class-specific estimation significantly outperforms pooled estimation methods, as quantified by a Jensen penalty.
  • The study provides theoretical constraints for fraud detection, emphasizing the need for tailored detection strategies.
Read more
BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies
Anya Singh, Cabrel Happi, Jai Relan, Varun Nair, Vidyut Baradwaj
Robotics Theory Multimodal
  • BOKBO is the first conformal abstention layer for K-sample VLA inference, providing safety guarantees.
  • The method achieves high reliability and task success rates while addressing silent failures in traditional K-sampling.
  • A critical analysis reveals that existing nonconformity scores fail to measure policy uncertainty accurately.
  • The introduction of a learned violation predictor improves safety calibration significantly.
Read more
Learning Multi-Agent Coordination via Sheaf-ADMM
Jeffrey Seely, Bartłomiej Cupiał, Llion Jones
Optimization Graph Learning Robotics
  • Introduces Sheaf-ADMM, a framework for multi-agent coordination using differentiable optimization.
  • Utilizes cellular sheaf theory to define inter-agent constraints for heterogeneous global consensus.
  • Demonstrates improved robustness and performance in tasks like MNIST classification and Sudoku solving.
  • Enables distinct analysis of coordination dynamics through the separation of state variables.
Read more