Machine Learning

ConFrag, a novel approach to noisy label regression, leverages contrastive fragmentation and neighborhood agreement to select clean samples, significantly outperforming state-of-the-art baselines on s…

SampDetox uses diffusion models to purify poisoned machine learning samples by strategically adding noise to eliminate backdoors without compromising data integrity.

SAMPa: Parallelizing gradient computations in Sharpness-Aware Minimization (SAM) achieves a 2x speedup and superior generalization.

Reinforcement Learning from Safety Feedback (RLSF) efficiently infers cost functions from trajectory-level feedback, enabling safe policy learning in complex environments.

SAFE, a novel parameter-efficient tuning framework, boosts pre-trained model performance in continual learning by balancing model stability and plasticity through slow and fast learning stages, signif…

A novel primal-dual method boosts offline safe reinforcement learning efficiency for convex CMDPs by using uncertainty parameters and achieving a sample complexity of O(1/(1-γ)√n).

S2HPruner bridges the discretization gap in neural network pruning via a novel soft-to-hard distillation framework, achieving superior performance across various benchmarks without fine-tuning.

S-MolSearch: a novel semi-supervised framework using 3D molecular data and contrastive learning achieves state-of-the-art in bioactive molecule search, outperforming existing methods.

Rough Transformers: A lightweight continuous-time sequence modeling approach using path signatures to significantly reduce computational costs, improving efficiency and accuracy, particularly for long…

ROIDICE: A novel offline reinforcement learning algorithm maximizes Return on Investment (ROI) by formulating the problem as linear fractional programming, yielding superior return-cost trade-offs.

This paper introduces robust reinforcement learning with general utility, providing novel algorithms with convergence guarantees for training robust policies under environmental uncertainty, significa…

R³M enhances reinforcement learning from human feedback by robustly handling corrupted preference labels, consistently learning the underlying reward and identifying outliers with minimal computationa…

This paper introduces a novel offline active learning method for node-level tasks on graphs, incorporating network structure and node covariates to improve efficiency and robustness, especially in noi…

This paper introduces robust group inference procedures for high-dimensional single index models, offering substantial efficiency gains for heavy-tailed errors and handling group testing effectively w…

Robust Gaussian Processes via Relevance Pursuit tackles noisy data by cleverly inferring data-point specific noise levels, leading to more accurate predictions.

CANDY refines contrastive multi-view clustering by cleverly using inter-view similarities to identify and correct false negatives and a spectral method to remove false positives, resulting in signific…

Temporal Optimal Transport (TemporalOT) reward enhances robot policy learning by incorporating temporal order information into Optimal Transport (OT)-based proxy rewards, leading to improved accuracy …

RMLR: A novel framework extends multinomial logistic regression to diverse geometries, overcoming limitations of existing methods by requiring minimal geometric properties for broad applicability.

First sample-efficient algorithm for LMDPs without separation assumptions, achieving near-optimal guarantees via novel off-policy evaluation.

Risk-sensitive control is recast as inference using Rényi divergence, yielding new algorithms and revealing equivalences between seemingly disparate methods.