Machine Learning

SMAG, a novel single-loop stochastic algorithm, achieves state-of-the-art convergence for solving non-smooth non-convex optimization problems involving differences of max-structured weakly convex func…

Train Neural ODEs without simulations, achieving high performance on regression and classification by using flow matching in the embedding space of data pairs.

This paper introduces the Parsimonious Latent Space Model (PLSM), a novel world model that regularizes latent dynamics to improve action predictability, enhancing RL performance.

This paper simplifies constraint inference in reinforcement learning, demonstrating that standard inverse RL methods can effectively infer constraints from expert data, surpassing complex, previously …

SNAPS: a novel algorithm boosts graph neural network accuracy by efficiently aggregating non-conformity scores, improving prediction sets without sacrificing validity.

Sigmoid gating significantly boosts sample efficiency in Mixture of Experts models compared to softmax gating, offering faster convergence rates for various expert functions.

SharpBalance, a novel training approach, effectively improves deep ensemble performance by addressing the sharpness-diversity trade-off, leading to significant improvements in both in-distribution and…

TS-LDDMM: Unsupervised time-series analysis handles irregular data, offering interpretable shape-based representations & exceeding existing methods in benchmarks.

Shadowheart SGD achieves optimal time complexity for asynchronous SGD in distributed settings with arbitrary computation and communication heterogeneity.

Set-based Neural Network Encoder (SNE) efficiently encodes neural network weights for property prediction, eliminating the need for architecture-specific models and improving generalization across dat…

SequentialAttention++ unites differentiable pruning with combinatorial optimization for efficient and accurate neural network block sparsification, achieving state-of-the-art results.

This paper introduces a novel, label-free method for detecting harmful distribution shifts in machine learning models deployed in production environments, leveraging a proxy error derived from an erro…

ExPerior leverages expert demonstrations to enhance online decision-making, even when experts use hidden contextual information unseen by the learner.

DANCE, a novel semi-supervised framework, efficiently transfers cell types across multi-omic single-cell data even with limited labeled samples, outperforming current state-of-the-art methods.

Self-Supervised Transformation Learning (STL) enhances equivariant representations by replacing transformation labels with image-pair-derived representations, improving performance on diverse classifi…

DAQ-SDP enhances self-supervised adversarial training by using diverse augmented queries, a self-supervised double perturbation scheme, and a novel Aug-Adv Pairwise-BatchNorm method, bridging the gap …

Self-Refining Diffusion Samplers (SRDS) dramatically speeds up diffusion model sampling by leveraging Parareal iterations for parallel-in-time computation, maintaining high-quality outputs.

Self-Labeling Improves Generative Model Training for Combinatorial Problems

Self-healing machine learning (SHML) autonomously diagnoses and fixes model performance degradation caused by data shifts, outperforming reason-agnostic methods.

SEL-BALD tackles the challenge of human discretion in active learning by proposing novel algorithms that account for instance rejection, significantly boosting sample efficiency.