Hao-Jun Michael Shi

19 papers A* 2Misc 1Journal 16

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent. CoRR Hiroki Naganuma, Shagun Gupta, Youssef Briki, Ioannis Mitliagkas, Irina Rish, Parameswaran Raman, Hao-Jun Michael Shi
2026	J	`jnl`	Clarifying Shampoo: Adapting Spectral Descent to Stochasticity and the Parameter Trajectory. CoRR Runa Eschenhagen, Anna Cai, Tsung-Hsien Lee, Hao-Jun Michael Shi
2025	J	`jnl`	Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner. CoRR Runa Eschenhagen, Aaron Defazio, Tsung-Hsien Lee, Richard E. Turner, Hao-Jun Michael Shi
2025	J	`jnl`	SNOO: Step-K Nesterov Outer Optimizer - The Surprising Effectiveness of Nesterov Momentum Applied to Pseudo-Gradients. CoRR Dominik Kallusky, Vinay Rao, Vishal Nandavanam, Hao-Jun Michael Shi
2025	J	`jnl`	Smoothing DiLoCo with Primal Averaging for Faster Training of LLMs. CoRR Aaron Defazio, Konstantin Mishchenko, Parameswaran Raman, Hao-Jun Michael Shi, Lin Xiao
2023	J	`jnl`	A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale. CoRR Hao-Jun Michael Shi, Tsung-Hsien Lee, Shintaro Iwasaki, Jose Gallego-Posada, Zhijing Li, Kaushik Rangadurai, Dheevatsa Mudigere, Michael Rabbat
2023	J	`jnl`	On the numerical performance of finite-difference-based methods for derivative-free optimization. Optim. Methods Softw. Hao-Jun Michael Shi, Melody Qiming Xuan, Figen Öztoprak, Jorge Nocedal
2022	J	`jnl`	A Noise-Tolerant Quasi-Newton Algorithm for Unconstrained Optimization. SIAM J. Optim. Hao-Jun Michael Shi, Yuchen Xie, Richard H. Byrd, Jorge Nocedal
2022	J	`jnl`	Adaptive Finite-Difference Interval Estimation for Noisy Derivative-Free Optimization. SIAM J. Sci. Comput. Hao-Jun Michael Shi, Yuchen Xie, Melody Qiming Xuan, Jorge Nocedal
2020	A*	`conf`	Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems. KDD Hao-Jun Michael Shi, Dheevatsa Mudigere, Maxim Naumov, Jiyan Yang
2019	J	`jnl`	Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems. CoRR Hao-Jun Michael Shi, Dheevatsa Mudigere, Maxim Naumov, Jiyan Yang
2019	J	`jnl`	Deep Learning Recommendation Model for Personalization and Recommendation Systems. CoRR Maxim Naumov, Dheevatsa Mudigere, Hao-Jun Michael Shi, Jianyu Huang, Narayanan Sundaraman, Jongsoo Park, Xiaodong Wang, Udit Gupta, Carole-Jean Wu, Alisson G. Azzolini, Dmytro Dzhulgakov, Andrey Mallevich, Ilia Cherniavskii, Yinghai Lu, Raghuraman Krishnamoorthi, Ansha Yu, Volodymyr Kondratenko, Stephanie Pereira, Xianjie Chen, Wenlin Chen, Vijay Rao, Bill Jia, Liang Xiong, Misha Smelyanskiy
2018	A*	`conf`	A Progressive Batching L-BFGS Method for Machine Learning. ICML Raghu Bollapragada, Dheevatsa Mudigere, Jorge Nocedal, Hao-Jun Michael Shi, Ping Tak Peter Tang
2018	J	`jnl`	A Progressive Batching L-BFGS Method for Machine Learning. CoRR Raghu Bollapragada, Dheevatsa Mudigere, Jorge Nocedal, Hao-Jun Michael Shi, Ping Tak Peter Tang
2018	J	`jnl`	Optimizing Quantization for Lasso Recovery. IEEE Signal Process. Lett. Xiaoyi Gu, Shenyinying Tu, Hao-Jun Michael Shi, Mindy Case, Deanna Needell, Yaniv Plan
2016	Misc	`conf`	Methods for quantized compressed sensing. ITA Hao-Jun Michael Shi, Mindy Case, Xiaoyi Gu, Shenyinying Tu, Deanna Needell
2016	J	`jnl`	Optimizing quantization for Lasso recovery. CoRR Xiaoyi Gu, Shenyinying Tu, Hao-Jun Michael Shi, Mindy Case, Deanna Needell, Yaniv Plan
2016	J	`jnl`	Practical Algorithms for Learning Near-Isometric Linear Embeddings. CoRR Jerry Luo, Kayla Shapiro, Hao-Jun Michael Shi, Qi Yang, Kan Zhu
2015	J	`jnl`	Methods for Quantized Compressed Sensing. CoRR Hao-Jun Michael Shi, Mindy Case, Xiaoyi Gu, Shenyinying Tu, Deanna Needell