Machine Learning

Self-supervised learning gets a boost: New objective function trains robust & predictive neural networks by straightening video trajectories, surpassing invariance methods for better spatiotemporal re…

Learn on massive graphs efficiently using Intersecting Community Graphs (ICGs)! This method approximates large graphs with ICGs, enabling linear time/memory complexity for node classification.

DDiffPG: A novel actor-critic algorithm learns multimodal policies from scratch using diffusion models, enabling agents to master versatile behaviors in complex tasks.

Learn macroscopic dynamics efficiently using only partial microscopic force computations! This novel method leverages sparsity assumptions and stochastic estimation for accurate, cost-effective modeli…

Learn continuous symmetries from data without pre-defined groups using Neural ODEs and a novel validity score to improve model generalization and efficiency.

Learning against adaptive adversaries in Markov games is hard, but this paper shows how to achieve low policy regret with efficient algorithms by introducing a new notion of consistent adaptive advers…

First-ever sublinear regret & constraint violation bounds achieved for infinite horizon average reward CMDPs with general policy parametrization using a novel primal-dual policy gradient algorithm.

Boost deep learning generalization with Learning from Teaching (LOT)! LOT trains auxiliary ‘student’ models to imitate a primary ’teacher’ model, improving the teacher’s ability to capture generalizab…

This paper introduces AdaptCDRP, a novel algorithm that uses conditional distributionally robust optimization to build robust classifiers from noisy labels, achieving superior accuracy.

OPCR, a novel one-step spatio-temporal imputation method, surpasses existing iterative approaches by directly propagating limited observations to the global context, achieving superior accuracy and ef…

Neural networks learn efficiently from higher-order correlations, exceeding the capabilities of random features, as demonstrated through hypothesis tests and novel theoretical analysis in high-dimensi…

AI agents efficiently learn Nash equilibria in adversarial team Markov games using a novel learning algorithm with polynomial complexity, resolving prior limitations.

Manifold Free-Form Flows (M-FFF) achieves fast and accurate generative modeling on Riemannian manifolds using a single function evaluation, outperforming prior methods.

Contrastive Trajectory Representation (CTR) boosts multi-agent reinforcement learning by learning distinguishable agent trajectories using contrastive loss, thus improving performance significantly.

This research introduces an Expectation-Maximization algorithm to train diffusion models from incomplete and noisy data, enabling their use in data-scarce scientific applications.

Layer-Adaptive STate pruning (LAST) optimizes deep state space models by efficiently reducing state dimensions, improving performance and scalability without retraining.

Latent Plan Transformer (LPT) solves long-term planning challenges in reinforcement learning by using latent variables to connect trajectory generation with final returns, achieving competitive result…

Humans autonomously select goals based on both observed and latent learning progress, impacting goal-conditioned policy learning.

Latent Functional Maps (LFM) offers a novel spectral framework for comparing, aligning, and transferring neural network representations, boosting downstream task performance and interpretability.

New CRL algorithms guarantee global convergence, handle multiple constraints and various risk measures, improving safety and robustness in AI.