Search Results for author:
Found 6 papers, 1 papers with code
Teaching Large Language Models to Reason with Reinforcement Learning
Surprisingly, we find the sample complexity of Expert Iteration is similar to that of PPO, requiring at most on the order of $10^6$ samples to converge from a pretrained checkpoint.
Understanding the Effect of Noise in LLM Training Data with Algorithmic Chains of Thought
We then evaluate the test performance of pretrained models both prompted and fine-tuned on noised datasets with varying levels of dataset contamination and intensity.
DFU: scale-robust diffusion model for zero-shot super-resolution image generation
Diffusion generative models have achieved remarkable success in generating images with a fixed resolution.
Deep Nonparametric Estimation of Intrinsic Data Structures by Chart Autoencoders: Generalization Error and Robustness
Our paper establishes statistical guarantees on the generalization error of chart autoencoders, and we demonstrate their denoising capabilities by considering $n$ noisy training samples, along with their noise-free counterparts, on a $d$-dimensional manifold.
On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds
Many existing experiments have demonstrated that generative networks can generate high-dimensional complex data from a low-dimensional easy-to-sample distribution.
Khinchin-type inequalities via Hadamard's factorisation
We prove Khinchin-type inequalities with sharp constants for type L random variables and all even moments.
Probability
