Machine Learning

HOAM learns reduced models of population dynamics for complex systems, enabling fast predictions across various physics parameters, outperforming state-of-the-art techniques.

Parameter-free optimization is revolutionized! Inexact Polyak Stepsize achieves the same convergence rate as clipped gradient descent but without any hyperparameter tuning, saving time and computatio…

FDCR defends against backdoor attacks in heterogeneous federated learning by identifying malicious clients via Fisher Information-based parameter importance discrepancies and rescaling crucial paramet…

PaMoRL framework boosts model-based reinforcement learning speed by parallelizing model and policy learning stages over sequence length, maintaining high sample efficiency.

PageRank Bandits (PRB) revolutionizes link prediction by framing it as a sequential decision-making problem, thus enabling the system to adapt to evolving data. Combining contextual bandits with PageR…

PACE, a novel neural operator, achieves unprecedented accuracy and speed in optical field simulation for complex photonic devices, surpassing existing methods by significantly reducing errors and boos…

P2C2Net: A physics-encoded neural network efficiently predicts complex spatiotemporal dynamics using coarse grids and limited training data, achieving state-of-the-art results.

OwMatch: a novel framework conquering open-world semi-supervised learning challenges by combining conditional self-labeling and consistency for substantially enhanced accuracy across known and unknown…

Leveraging simulation for real-world RL is often hampered by the sim-to-real gap. This paper shows that instead of directly transferring policies, transferring exploratory policies from simulation d…

Boost OOD detection accuracy with diverseMix: a novel method enhancing auxiliary outlier diversity, provably improving generalization and achieving state-of-the-art results.

Single diffusion model achieves competitive out-of-distribution detection across diverse tasks by analyzing diffusion path characteristics.

OTTER effortlessly adapts zero-shot models to new tasks by adjusting predictions using optimal transport, improving accuracy significantly without extra training data.

Ordered Momentum (OrMo) significantly boosts asynchronous stochastic gradient descent (ASGD) convergence by cleverly incorporating momentum, resolving prior convergence issues. This novel approach is…

Boost RL performance in large state spaces by efficiently learning a policy competitive with the best combination of existing base policies!

This paper proposes ‘generalized quasar-convexity’ to optimize problems with multiple probability distributions, offering adaptive algorithms with superior iteration complexities compared to existing …

Researchers developed a verifiable training method that uses high-precision training with adaptive rounding and logging to achieve exact training replication across different GPUs, enabling efficient …

This paper introduces OCR-CFT, a novel method for general offline-to-online RL, achieving stable and efficient performance improvements by addressing evaluation and improvement mismatches through opti…

Optimal Top-Two Algorithm solves best arm identification problem with improved efficiency and computational cost, achieving asymptotic optimality.

Vector-valued spectral learning algorithms finally get rigorous theoretical backing, showing optimal learning rates and resolving the saturation effect puzzle.

This paper derives matching minimax bounds for distributed goodness-of-fit testing of discrete data under bandwidth or privacy constraints, bridging theory and practice in federated learning.