Machine Learning

LinUProp: Linearly scalable uncertainty quantification for graphical models, achieving higher accuracy with lower labeling budgets!

Linear transformers surprisingly learn intricate optimization algorithms, even surpassing baselines on noisy regression problems, showcasing their unexpected learning capabilities.

LightUnbalancedOptimalTransport: A fast, theoretically-justified solver for continuous unbalanced optimal transport problems, enabling efficient analysis of large datasets with imbalanced classes.

LFME: A novel framework improves domain generalization by training multiple expert models alongside a target model, using logit regularization for enhanced performance.

SeeX, a novel bi-level optimization framework, effectively tackles the challenge of exploration in visually cluttered environments by training a separated world model to extract relevant information a…

New gradient coding protocols efficiently leverage partial results from slow worker nodes, accelerating distributed training by approximately 2x and significantly improving accuracy.

Drifted VESDE: Faster convergence, efficient sampling for variance-exploding diffusion models!

GCFormer, a novel graph Transformer, enhances node representation learning by employing a hybrid token generator and contrastive learning, outperforming existing methods on various datasets.

MUN: a novel goal-directed exploration algorithm significantly improves world model reliability and policy generalization in sparse-reward goal-conditioned RL, enabling efficient navigation across div…

Surrogate PAC-Bayes Learning (SuPAC) efficiently optimizes generalization bounds by iteratively optimizing surrogate training objectives, enabling faster and more scalable learning for complex models.

CurrMask: a novel curriculum masking paradigm for offline RL, achieving superior zero-shot and fine-tuning performance by dynamically adjusting masking schemes during pretraining, enabling versatile s…

Deterministically shaping in-distribution feature space solves OOD detection’s distributional assumption challenge, leading to superior performance.

Deep learning predicts structural vibrations faster than traditional methods, reducing noise in airplanes, cars, and buildings, as shown by a new benchmark and frequency-query operator network.

Learn optimal data-dependent distribution kernels via Maximum Kernel Entropy, eliminating manual kernel selection and boosting performance on various downstream tasks.

AI agents learn to balance helpfulness and self-preservation using empathy to gauge social relationships and guide reward sharing.

A novel Decomposition-based Policy Learning (DPPL) method optimally balances short-term and long-term rewards, even with interrelated objectives, by transforming the problem into intuitive subproblems…

Learning latent causal structures improves label noise modeling by accurately estimating noise transition matrices without relying on similarity-based assumptions, leading to state-of-the-art classifi…

Learn infinitesimal generators of stochastic diffusion processes efficiently via a novel energy-based risk functional, overcoming the unbounded nature of the generator and providing learning bounds in…

Learn data symmetries directly from data with flexible weight-sharing using learnable doubly stochastic tensors!

Learn deep Successor Features (SFs) directly from pixels, efficiently and without representation collapse, using a novel, simple method combining TD and reward prediction loss!