3 citations · 10 across the 17 of their papers we have counts for
18 papers
Shallow Queries, Mature Values: Depth-Asynchronous Self-Speculation for Looped Transformers
Guanghao Li, Zihan Su, Hao Yu +6
Looped Transformers reuse a shared block across recurrent depths, making autoregressive decoding expensive because every generated token requires many sequential recurrent passes.…
Adaptive Robust Estimator for Multi-Agent Reinforcement Learning
Zhongyi Li, Wan Tian, Jingyu Chen +8
Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from interaction-level ambiguity that…
Omni-Masked Gradient Descent: Memory-Efficient Optimization via Mask Traversal with Improved Convergence
Hui Yang, Tao Ren, Jinyang Jiang +2
Memory-efficient optimization methods have recently gained increasing attention for scaling full-parameter training of large language models under the GPU-memory bottleneck. Existi…
Stochastic Approximation Methods for Distortion Risk Measure Optimization
Jinyang Jiang, Bernd Heidergott, Jiaqiao Hu +1
Distortion Risk Measures (DRMs) capture risk preferences in decision-making and serve as general criteria for managing uncertainty. This paper proposes gradient descent algorithms…
RiskPO: Risk-based Policy Optimization via Verifiable Reward for LLM Post-Training
Tao Ren, Jinyang Jiang, Hui Yang +10
Reinforcement learning with verifiable reward has recently emerged as a central paradigm for post-training large language models (LLMs); however, prevailing mean-based methods, suc…
Forward Learning with Differential Privacy
Mingqian Feng, Zeliang Zhang, Jinyang Jiang +2
Differential privacy (DP) in deep learning is a critical concern as it ensures the confidentiality of training data while maintaining model utility. Existing DP training algorithms…
CoNNect: Connectivity-Based Regularization for Structural Pruning
Christian Franssen, Jinyang Jiang, Yijie Peng +1
Pruning encompasses a range of techniques aimed at increasing the sparsity of neural networks (NNs). These techniques can generally be framed as minimizing a loss function subject…
Integrated Offline and Online Learning to Solve a Large Class of Scheduling Problems
Anbang Liu, Zhi-Long Chen, Jinyang Jiang +1
In this paper, we develop a unified machine learning (ML) approach to predict high-quality solutions for single-machine scheduling problems with a non-decreasing min-sum objective…
A Parameter-Efficient Quantum Anomaly Detection Method on a Superconducting Quantum Processor
Maida Wang, Jinyang Jiang, Peter V. Coveney
Quantum machine learning has gained attention for its potential to address computational challenges. However, whether those algorithms can effectively solve practical problems and…
FLOPS: Forward Learning with OPtimal Sampling
Tao Ren, Zishi Zhang, Jinyang Jiang +4
Given the limitations of backpropagation, perturbation-based gradient computation methods have recently gained focus for learning with only forward passes, also referred to as quer…
Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training
Zeliang Zhang, Jinyang Jiang, Zhuo Liu +3
Efficient and biologically plausible alternatives to backpropagation in neural network training remain a challenge due to issues such as high computational complexity and additiona…
Forward Learning for Gradient-based Black-box Saliency Map Generation
Zeliang Zhang, Mingqian Feng, Jinyang Jiang +3
Gradient-based saliency maps are widely used to explain deep neural network decisions. However, as models become deeper and more black-box, such as in closed-source APIs like ChatG…
Deep Reinforcement Learning for Solving Management Problems: Towards A Large Management Mode
Jinyang Jiang, Xiaotian Liu, Tao Ren +5
We introduce a deep reinforcement learning (DRL) approach for solving management problems including inventory management, dynamic pricing, and recommendation. This DRL approach has…
RiskMiner: Discovering Formulaic Alphas via Risk Seeking Monte Carlo Tree Search
Tao Ren, Ruihan Zhou, Jinyang Jiang +3
The formulaic alphas are mathematical formulas that transform raw stock data into indicated signals. In the industry, a collection of formulaic alphas is combined to enhance modeli…
Quantile-Based Deep Reinforcement Learning using Two-Timescale Policy Gradient Algorithms
Jinyang Jiang, Jiaqiao Hu, Yijie Peng
Classical reinforcement learning (RL) aims to optimize the expected cumulative reward. In this work, we consider the RL setting where the goal is to optimize the quantile of the cu…
One Forward is Enough for Neural Network Training via Likelihood Ratio Method
Jinyang Jiang, Zeliang Zhang, Chenliang Xu +2
While backpropagation (BP) is the mainstream approach for gradient computation in neural network training, its heavy reliance on the chain rule of differentiation constrains the de…
A Novel Noise Injection-based Training Scheme for Better Model Robustness
Zeliang Zhang, Jinyang Jiang, Minjie Chen +3
Noise injection-based method has been shown to be able to improve the robustness of artificial neural networks in previous work. In this work, we propose a novel noise injection-ba…
Quantile-Based Policy Optimization for Reinforcement Learning
Jinyang Jiang, Jiaqiao Hu, Yijie Peng
Classical reinforcement learning (RL) aims to optimize the expected cumulative rewards. In this work, we consider the RL setting where the goal is to optimize the quantile of the c…