Machine Learning

Boosting neural network surface processing: Using principal curvatures as input significantly improves segmentation and classification accuracy while reducing computational overhead.

Accelerate Gaussian process hyperparameter optimization by up to 72x using novel linear system solver techniques.

IRE framework expedites the discovery of flat minima in deep learning, enhancing generalization and convergence. By decoupling the dynamics of flat and sharp directions, IRE boosts sharpness reduction…

Boost equivariant model training by strategically relaxing constraints during training, enhancing optimization and generalization!

Deep RL agents often suffer from instability due to the ‘chain effect’ of value and policy churn; this paper introduces CHAIN, a novel method to reduce this churn, thereby improving DRL performance an…

Constrained Parameter Regularization (CPR) outperforms traditional weight decay by dynamically adapting regularization strengths for individual parameters, leading to better deep learning model perfor…

This paper significantly improves our understanding of multiclass PAC learning by reducing the sample complexity gap and proposing two novel approaches to fully resolve the optimal sample complexity.

Training high-quality diffusion models efficiently is now possible, thanks to novel sample complexity bounds improving exponentially on previous work.

Linear ensemble sampling achieves a state-of-the-art regret bound of Õ(d³/²√T) with a logarithmic ensemble size, closing the theory-practice gap in linear bandit algorithms.

Researchers enhanced diffusion samplers by developing a novel exploration strategy and a unified library, improving sample quality and addressing reproducibility challenges.

New modeling of bid space in multi-unit uniform price auctions achieves regret of Õ(K4/3T2/3) under bandit feedback, improving over prior work and closing the gap with discriminatory pricing.

This paper significantly improves Bayes regret bounds for hierarchical Bayesian bandit algorithms, achieving logarithmic regret in finite action settings and enhanced bounds in multi-task linear and c…

Unified framework for imprecise label learning handles noisy, partial, and semi-supervised data, improving model training efficiency and accuracy.

PropEn: a novel framework for implicitly guided design optimization that leverages ‘matching’ to boost efficiency by matching samples and approximating the gradient without a discriminator.

This paper introduces seq-NMF, a novel method for unsupervised subtask discovery in reinforcement learning that leverages selection variables to enhance generalization and data efficiency.

This study introduces a novel framework for individualized reinforcement learning, guaranteeing the identifiability of latent factors influencing state transitions and providing a practical method for…

Unsupervised group recommendation model, ITR, achieves superior user and group recommendation accuracy by dynamically identifying user groups and employing self-supervised learning, eliminating the ne…

Probabilistic Slot Attention achieves identifiable object-centric representations without supervision, advancing systematic generalization in machine learning.

HyperPrism, a novel framework, tackles challenges in distributed machine learning by using adaptive non-linear aggregation to handle non-IID data and dynamic communication links, significantly improvi…

HyperLogic uses hypernetworks to generate diverse, accurate, and concise rule sets from neural networks, enhancing both interpretability and accuracy in rule learning.