cs.LG papers | Gist.Science

SignalMC-MED: A Multimodal Benchmark for Evaluating Biosignal Foundation Models on Single-Lead ECG and PPG

The paper introduces SignalMC-MED, a comprehensive benchmark utilizing 22,256 synchronized single-lead ECG and PPG visits to evaluate biosignal foundation models across 20 clinical tasks, demonstrating that domain-specific models with multimodal fusion and full-duration signals outperform general time-series approaches while revealing that larger model sizes do not guarantee superior performance.

Fredrik K. Gustafsson, Xiao Gu, Mattia Carletti, Patitapaban Palo, David W. Eyre, David A. CliftonWed, 11 Ma🤖 cs.LG

Generative Drifting is Secretly Score Matching: a Spectral and Variational Perspective

This paper establishes that generative drifting is theoretically equivalent to score matching under Gaussian kernels, providing a spectral and variational framework that explains the empirical superiority of Laplacian kernels, proposes an exponential bandwidth annealing schedule to accelerate convergence, and proves the necessity of the stop-gradient operator through its connection to Wasserstein gradient flows.

Erkan Turan, Maks OvsjanikovWed, 11 Ma🤖 cs.LG

OptEMA: Adaptive Exponential Moving Average for Stochastic Optimization with Zero-Noise Optimality

This paper introduces OptEMA, a novel adaptive Exponential Moving Average optimizer that achieves nearly optimal convergence rates in both stochastic and zero-noise regimes without requiring prior knowledge of Lipschitz constants or manual hyperparameter tuning.

Ganzhao YuanWed, 11 Ma🤖 cs.LG

CarbonBench: A Global Benchmark for Upscaling of Carbon Fluxes Using Zero-Shot Learning

The paper introduces CarbonBench, the first standardized benchmark comprising over 1.3 million global observations from 567 sites, designed to rigorously evaluate and compare zero-shot spatial transfer learning methods for upscaling terrestrial carbon fluxes across diverse, unseen ecosystems and climate regimes.

Aleksei Rozanov, Arvind Renganathan, Yimeng Zhang, Vipin KumarWed, 11 Ma🤖 cs.LG

GAST: Gradient-aligned Sparse Tuning of Large Language Models with Data-layer Selection

The paper proposes GAST, a novel Parameter-Efficient Fine-Tuning method that unifies data-layer selection and layer-sparse strategies to adaptively match impactful data points with specific model layers, thereby overcoming the limitations of existing single-dimension approaches and achieving superior performance.

Kai Yao, Zhenghan Song, Kaixin Wu, Mingjie Zhong, Danzhao Cheng, Zhaorui Tan, Yixin Ji, Penglei GaoWed, 11 Ma🤖 cs.LG

A Unified Hierarchical Multi-Task Multi-Fidelity Framework for Data-Efficient Surrogate Modeling in Manufacturing

This paper proposes a novel hierarchical multi-task multi-fidelity (H-MT-MF) framework for Gaussian process-based surrogate modeling that unifies inter-task information sharing and fidelity-dependent uncertainty handling to significantly improve prediction accuracy and data efficiency in manufacturing systems with heterogeneous data sources.

Manan Mehta, Zhiqiao Dong, Yuhang Yang, Chenhui ShaoWed, 11 Ma🤖 cs.LG

Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning

This paper introduces In-Context RLVR, a method that leverages a model's own in-context learning ability to measure "Demonstration Utility" via Evidence Gain, thereby implicitly reweighting rewards to prioritize high-quality reasoning traces over merely correct but flawed solutions during Reinforcement Learning with Verifiable Rewards training.

Tiehua Mei, Minxuan Lv, Leiyu Pan, Zhenpeng Su, Hongru Hou, Hengrui Chen, Ao Xu, Deqing YangWed, 11 Ma🤖 cs.LG

Information Theoretic Bayesian Optimization over the Probability Simplex

This paper introduces $\alpha$ -GaBO, a novel family of Bayesian optimization algorithms that leverages information geometry to construct Matérn kernels and geometric optimizers tailored for the probability simplex, demonstrating superior performance over constrained Euclidean approaches in optimizing mixtures and robotic control tasks.

Federico Pavesi, Antonio Candelieri, Noémie JaquierWed, 11 Ma🤖 cs.LG

Upper Generalization Bounds for Neural Oscillators

This paper derives upper PAC generalization bounds for neural oscillators based on second-order ODEs and MLPs, demonstrating that their estimation errors grow polynomially with model size and time while showing that constraining MLP Lipschitz constants via regularization enhances generalization performance in modeling nonlinear structural systems.

Zifeng Huang, Konstantin M. Zuev, Yong Xia, Michael BeerWed, 11 Ma🤖 cs.LG

A Multi-Prototype-Guided Federated Knowledge Distillation Approach in AI-RAN Enabled Multi-Access Edge Computing System

This paper proposes a Multi-Prototype-Guided Federated Knowledge Distillation (MP-FedKD) approach for AI-RAN enabled Multi-Access Edge Computing systems, which addresses non-IID data challenges and mitigates information loss from single-prototype averaging by integrating self-knowledge distillation, a conditional hierarchical agglomerative clustering strategy, and a novel loss function to outperform state-of-the-art baselines in accuracy and error metrics.

Luyao Zou, Hayoung Oh, Chu Myaet Thwal, Apurba Adhikary, Seohyeon Hong, Zhu HanWed, 11 Ma🤖 cs.LG

On Catastrophic Forgetting in Low-Rank Decomposition-Based Parameter-Efficient Fine-Tuning

This paper empirically demonstrates that catastrophic forgetting in low-rank decomposition-based parameter-efficient fine-tuning is primarily driven by update subspace geometry, revealing that tensor-based and structurally aligned methods outperform traditional shared matrix approaches in sequential learning scenarios.

Muhammad Ahmad, Jingjing Zheng, Yankai CaoWed, 11 Ma🤖 cs.LG

No evaluation without fair representation : Impact of label and selection bias on the evaluation, performance and mitigation of classification models

This paper empirically analyzes the distinct impacts of label and selection bias on classification model evaluation and performance using a new framework for introducing controlled bias, revealing that fairness-accuracy trade-offs disappear when models are evaluated on unbiased data and demonstrating that the effectiveness of mitigation methods depends on the specific bias type present.

Magali Legast, Toon Calders, François FoussWed, 11 Ma🤖 cs.LG

FreqCycle: A Multi-Scale Time-Frequency Analysis Method for Time Series Forecasting

FreqCycle is a novel multi-scale time-frequency analysis framework that improves time series forecasting by combining a Filter-Enhanced Cycle module for low-frequency patterns and a Segmented Frequency-domain module for mid-to-high frequencies, further extended to MFreqCycle to decouple coupled multi-periodicity, thereby achieving state-of-the-art accuracy with efficient inference.

Boya Zhang, Shuaijie Yin, Huiwen Zhu, Xing HeWed, 11 Ma🤖 cs.LG

Well Log-Guided Synthesis of Subsurface Images from Sparse Petrography Data Using cGANs

This paper presents a conditional Generative Adversarial Network (cGAN) framework that synthesizes realistic, continuous pore-scale images of carbonate rock formations by conditioning on well log-derived porosity values, effectively bridging gaps between sparse petrography samples to enhance reservoir characterization for energy transition applications.

Ali Sadeghkhani, A. Assadi, B. Bennett, A. RabbaniWed, 11 Ma🤖 cs.LG

Learning the Hierarchical Organization in Brain Network for Brain Disorder Diagnosis

The paper proposes BrainHO, a novel framework that learns intrinsic hierarchical brain network dependencies from fMRI data using a hierarchical attention mechanism and orthogonality constraints, thereby achieving state-of-the-art diagnosis performance and uncovering interpretable biomarkers for brain disorders without relying on predefined sub-network labels.

Jingfeng Tang, Peng Cao, Guangqi Wen, Jinzhu Yang, Xiaoli Liu, Osmar R. ZaianeWed, 11 Ma🤖 cs.LG

MM-algorithms for traditional and convex NMF with Tweedie and Negative Binomial cost functions and empirical evaluation

This paper presents a unified framework for traditional and convex Non-negative Matrix Factorization (NMF) under Negative Binomial and Tweedie distributions, deriving novel multiplicative update rules via Majorize-Minimization and demonstrating through empirical evaluation that appropriate noise model selection and convex formulations significantly improve feature recovery in overdispersed data.

Elisabeth Sommer James, Asger Hobolth, Marta PelizzolaWed, 11 Ma🤖 cs.LG

Memorization capacity of deep ReLU neural networks characterized by width and depth

This paper establishes the optimal trade-off between width and depth for deep ReLU neural networks to memorize $N$ separated data points, proving that the product of the squared width and squared depth must scale as $\Theta(N\log(\delta^{-1}))$ .

Xin Yang, Yunfei YangWed, 11 Ma🤖 cs.LG

Nonparametric Variational Differential Privacy via Embedding Parameter Clipping

This paper introduces a theoretically grounded parameter clipping strategy derived from Rényi Divergence minimization to stabilize training and improve the privacy-utility trade-off in nonparametric variational differential privacy models by preventing learned latent representations from drifting into high-information regions.

Dina El Zein, Shashi Kumar, James HendersonWed, 11 Ma🤖 cs.LG

Towards Understanding Adam Convergence on Highly Degenerate Polynomials

This paper theoretically demonstrates that Adam naturally achieves local linear convergence on highly degenerate polynomials through a decoupling mechanism that amplifies the effective learning rate, significantly outperforming Gradient Descent and Momentum without requiring external schedulers.

Zhiwei Bai, Jiajie Zhao, Zhangchen Zhou, Zhi-Qin John Xu, Yaoyu ZhangWed, 11 Ma🤖 cs.LG

An Optimal Control Approach To Transformer Training

This paper proposes a rigorous optimal control framework that models Transformer training as a lifted Markov decision process on probability measures, establishing the existence of globally optimal policies and providing a quantized, gradient-free training alternative that respects key architectural constraints like input independence and positional encoding.

Ka\u{g}an Akman, Naci Saldı, Serdar YükselWed, 11 Ma🤖 cs.LG

← Previous Next →