15 citations · 49 across the 17 of their papers we have counts for
19 papers
TrainBridge: Agentic NPU Training Optimization Guided by GPU Compilation Evidence
Yupeng Chen, Kunxiang Zhao, Xingjian Wang +6
We study how to improve training efficiency on Ascend NPUs. In the NPU training programs we study, framework-level compilation optimizations such as operator fusion are only partia…
Towards Better Training Signal: Advantage Clipped Policy Optimization
Ruichuan Huang, Jinghan Liu, Congliang Chen
Reinforcement learning (RL) has become a cornerstone for improving the reasoning capabilities of large language models (LLMs), but the need for on-policy data substantially limits…
Off-Policy Value-Based Reinforcement Learning for Large Language Models
Peng-Yuan Wang, Ziniu Li, Tian Xu +8
Improving data utilization efficiency is critical for scaling reinforcement learning (RL) for long-horizon tasks where generating trajectories is expensive. However, the dominant R…
Adam Converges Without Any Modification On Update Rules
Yushun Zhang, Bingran Li, Congliang Chen +2
Adam is the default algorithm for training neural networks, including large language models (LLMs). However, \citet{reddi2019convergence} provided an example that Adam diverges, ra…
ORGEval: Graph-Theoretic Evaluation of LLMs in Optimization Modeling
Zhuohan Wang, Ziwei Zhu, Ziniu Li +8
Formulating optimization problems for industrial applications demands significant manual effort and domain expertise. While Large Language Models (LLMs) show promise in automating…
Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Ziniu Li, Congliang Chen, Tianyun Yang +5
Large Language Models (LLMs) can self-improve through reinforcement learning, where they generate trajectories to explore and discover better solutions. However, this exploration p…
Rethinking Data Mixture for Large Language Models: A Comprehensive Survey and New Perspectives
Yajiao Liu, Congliang Chen, Junchi Yang +1
Training large language models with data collected from various domains can improve their performance on downstream tasks. However, given a fixed training budget, the sampling prop…
AdaGC: Enhancing LLM Pretraining Stability via Adaptive Gradient Clipping
Guoxia Wang, Shuai Li, Congliang Chen +5
Loss spikes remain a persistent obstacle in large-scale language model pretraining. While previous research has attempted to identify the root cause of loss spikes by investigating…
Exploring the Generalization Capabilities of AID-based Bi-level Optimization
Congliang Chen, Li Shen, Zhiqiang Xu +3
Bi-level optimization has achieved considerable success in contemporary machine learning applications, especially for given proper hyperparameters. However, due to the two-level op…
Preserving Diversity in Supervised Fine-Tuning of Large Language Models
Ziniu Li, Congliang Chen, Tian Xu +4
Large Language Models (LLMs) typically rely on Supervised Fine-Tuning (SFT) to specialize in downstream tasks, with the Cross Entropy (CE) loss being the de facto choice. However,…
Adam-mini: Use Fewer Learning Rates To Gain More
Yushun Zhang, Congliang Chen, Ziniu Li +6
We propose Adam-mini, an optimizer that achieves on par or better performance than AdamW with 50% less memory footprint. Adam-mini reduces memory by cutting down the learning rate…
Why Transformers Need Adam: A Hessian Perspective
Yushun Zhang, Congliang Chen, Tian Ding +3
SGD performs worse than Adam by a significant margin on Transformers, but the reason remains unclear. In this work, we provide an explanation through the lens of Hessian: (i) Trans…
Rethinking SIGN Training: Provable Nonconvex Acceleration without First- and Second-Order Gradient Lipschitz
Tao Sun, Congliang Chen, Peng Qiao +3
Sign-based stochastic methods have gained attention due to their ability to achieve robust performance despite using only the sign information for parameter updates. However, the c…
Adam Can Converge Without Any Modification On Update Rules
Yushun Zhang, Congliang Chen, Naichen Shi +2
Ever since Reddi et al. 2018 pointed out the divergence issue of Adam, many new variants have been designed to obtain convergence. However, vanilla Adam remains exceptionally popul…
Efficient-Adam: Communication-Efficient Distributed Adam
Congliang Chen, Li Shen, Wei Liu +1
Distributed adaptive stochastic gradient methods have been widely used for large-scale nonconvex optimization, such as training deep learning models. However, their communication c…
Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration
Congliang Chen, Li Shen, Fangyu Zou +1
Adam is one of the most influential adaptive stochastic algorithms for training deep neural networks, which has been pointed out to be divergent even in the simple convex setting v…
Quantized Adam with Error Feedback
Congliang Chen, Li Shen, Haozhi Huang +1
In this paper, we present a distributed variant of adaptive stochastic gradient method for training deep neural networks in the parameter-server model. To reduce the communication…
A Unified Analysis of AdaGrad with Weighted Aggregation and Momentum Acceleration
Li Shen, Congliang Chen, Fangyu Zou +3
Integrating adaptive learning rate and momentum techniques into SGD leads to a large class of efficiently accelerated adaptive stochastic algorithms, such as AdaGrad, RMSProp, Adam…
Arbitrary Style Transfer with Deep Feature Reshuffle
Shuyang Gu, Congliang Chen, Jing Liao +1
This paper introduces a novel method by reshuffling deep features (i.e., permuting the spacial locations of a feature map) of the style image for arbitrary style transfer. We theor…