7 citations · 10 across the 8 of their papers we have counts for
8 papers
Elucidating Subspace Perturbation in Zeroth-Order Optimization: Theory and Practice at Scale
Sihwan Park, Jihun Yun, SungYub Kim +2
Zeroth-order (ZO) optimization has emerged as a promising alternative to gradient-based backpropagation methods, particularly for black-box optimization and large language model (L…
LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
Doohyuk Jang, Sihwan Park, June Yong Yang +5
Auto-Regressive (AR) models have recently gained prominence in image generation, often matching or even surpassing the performance of diffusion models. However, one major limitatio…
TEDDY: Trimming Edges with Degree-based Discrimination strategY
Hyunjin Seo, Jihun Yun, Eunho Yang
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…
Cluster-Promoting Quantization with Bit-Drop for Minimizing Network Quantization Loss
Jung Hyun Lee, Jihun Yun, Sung Ju Hwang +1
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 st…
A General Family of Stochastic Proximal Gradient Methods for Deep Learning
Jihun Yun, Aurelie C. Lozano, Eunho Yang
We study the training of regularized neural networks where the regularizer can be non-smooth and non-convex. We propose a unified framework for stochastic proximal gradient descent…
Semi-Relaxed Quantization with DropBits: Training Low-Bit Neural Networks via Bit-wise Regularization
Jung Hyun Lee, Jihun Yun, Sung Ju Hwang +1
Network quantization, which aims to reduce the bit-lengths of the network weights and activations, has emerged as one of the key ingredients to reduce the size of neural networks f…
Stochastic Gradient Methods with Block Diagonal Matrix Adaptation
Jihun Yun, Aurelie C. Lozano, Eunho Yang
Adaptive gradient approaches that automatically adjust the learning rate on a per-feature basis have been very popular for training deep networks. This rich class of algorithms inc…
M-estimation with the Trimmed l1 Penalty
Jihun Yun, Peng Zheng, Eunho Yang +2
We study high-dimensional estimators with the trimmed penalty, which leaves the largest parameter entries penalty-free. While optimization techniques for this nonconve…