🏢 Tel Aviv University

Warm-up-free policy optimization achieves rate-optimal regret in linear Markov decision processes, improving efficiency and dependence on problem parameters.

UDPM: Upsampling Diffusion Probabilistic Models achieves high-quality image generation with fewer computations by incorporating downsampling and upsampling within the diffusion process.

Gradient descent’s sample complexity in non-smooth stochastic convex optimization is Õ(d/m+1/√m), matching worst-case ERMs and showing no advantage over naive methods.

GNAN: a novel interpretable graph neural network achieving accuracy comparable to black-box models.

New research resolves discrepancies in language model scaling laws, revealing three key factors driving the differences and improving accuracy in predicting optimal model size based on compute budget.

Complex numbers boost neural network performance! This study proves that complex parameterizations in structured state space models (SSMs) enable more efficient and practical learning of complex mappi…

First algorithm for online weighted paging that learns page weights from samples, achieving optimal O(log k) competitiveness and sublinear regret.

Improved facility location mechanisms are designed using ‘Mostly Approximately Correct’ predictions, exceeding prior bounds despite large prediction errors.

New definitions of differential privacy enable machine learning algorithms to credit sources appropriately, balancing data utility and copyright compliance.