Machine Learning

LLM-powered Tri-level learning framework enhances time series OOD generalization.

TreeVI: Scalable tree-structured variational inference captures instance-level correlations for improved model accuracy.

Treeffuser: Accurate probabilistic predictions from tabular data using conditional diffusion models and gradient-boosted trees!

This paper presents a novel BayesOpt framework that incorporates Markov Decision Processes to optimize black-box functions with transition constraints, overcoming limitations of traditional methods.

Transformers surprisingly learn second-order optimization methods for in-context linear regression, achieving exponentially faster convergence than gradient descent!

Pre-trained transformers can provably learn to play games near-optimally using in-context learning, offering theoretical guarantees for both decentralized and centralized settings.

Transformers excel at in-context learning by leveraging minimax-optimal nonparametric learning, achieving near-optimal risk with sufficient pretraining data diversity.

This paper bridges the gap between synthetic and real image disentanglement by proposing a novel transfer learning approach. The method leverages weakly supervised learning on synthetic data to train…

Transferable Boltzmann Generators enable efficient, zero-shot sampling of unseen molecular systems’ equilibrium distributions, boosting molecular simulations.

This paper presents efficient algorithms for transfer learning in latent variable network models, achieving vanishing error under specific conditions, and attaining minimax optimal rates for stochasti…

This paper introduces transductive active learning, proving its efficiency in minimizing uncertainty and achieving state-of-the-art results in neural network fine-tuning and safe Bayesian optimization…

Offline RL with trajectory data achieves statistically efficient learning under linear q*-realizability and concentrability, solving a previously deemed impossible problem.

VISPA, a novel BNN training framework using Gaussian variational inference and low-rank SDP, achieves state-of-the-art accuracy on various benchmarks.

This work unveils a causal lens on extrapolation, offering theoretical guarantees for accurate predictions on out-of-support data, even with limited target samples.

This paper proposes a novel solution to the transferability problem in inverse reinforcement learning (IRL) using principal angles to measure the similarity between transition laws. It provides suffi…

ATProt: Adversarial training makes protein interface prediction robust to flexibility!

Analog in-memory computing (AIMC) training suffers from asymptotic errors due to asymmetric updates. This paper rigorously proves this limitation, proposes a novel discrete-time model to characterize …

Novel covariance-adaptive algorithms achieve optimal gap-free regret bounds for combinatorial semi-bandits, improving efficiency with sampling-based approaches.

N2: A novel dynamic message-passing GNN tackles message-passing bottlenecks and high computational costs by introducing learnable pseudo-nodes and dynamic pathways in a common state space, achieving s…

TAKFL, a novel federated learning framework, tackles device heterogeneity by independently distilling knowledge from diverse devices and integrating it adaptively, achieving state-of-the-art performan…