8 accepted papers
On-policy preference learning algorithms for language model alignment such as online direct policy optimization (DPO) can significantly outperform their offline counterparts. We provide a theoretical explanation for this phenomenon by analyzing how the sampling policy's coverage evolves throughout o…
Auto-Regressive (AR) models have recently gained prominence in image generation, often matching or even surpassing the performance of diffusion models. However, one major limitation of AR models is their sequential nature, which processes tokens one at a time, slowing down generation compared to mod…
Since the pioneering work on the lottery ticket hypothesis for graph neural networks (GNNs) was proposed in Chen et al. (2021), the study on finding graph lottery tickets (GLT) has become one of the pivotal focus in the GNN community, inspiring researchers to discover sparser GLT while achieving com…
Contemporary advances in the field of deep learning have embarked upon an exploration of the underlying geometric properties of data, thus encouraging the investigation of techniques that consider general manifolds, for example, hyperbolic or orthogonal neural networks. However, the optimization alg…
We introduce AdaBlock, a class of adaptive gradient methods that extends popular approaches such as Adam by adopting the simple and natural idea of using block-diagonal matrix adaption to effectively utilize structural characteristics of deep learning architectures. Unlike other quadratic or block-d…
We consider the training of structured neural networks where the regularizer can be non-smooth and possibly non-convex. While popular machine learning libraries have resorted to stochastic (adaptive) subgradient approaches, the use of proximal gradient methods in the stochastic setting has been litt…
Network quantization, which aims to reduce the bit-lengths of the network weights and activations, has emerged for their deployments to resource-limited devices. Although recent studies have successfully discretized a full-precision network, they still incur large quantization errors after training,…
We study high-dimensional estimators with the trimmed $\ell_1$ penalty, which leaves the h largest parameter entries penalty-free. While optimization techniques for this nonconvex penalty have been studied, the statistical properties have not yet been analyzed. We present the first statistical analy…