14 citations · 31 across the 10 of their papers we have counts for
10 papers
A Low-Latency Fraud Detection Layer for Detecting Adversarial Interaction Patterns in LLM-Powered Agents
Sheldon Yu, Yingcheng Sun, Hanqing Guo +1
Large Language Model (LLM)-powered agents demonstrate strong capabilities in autonomous task execution, tool use, and multi-step reasoning. However, their increasing autonomy also…
GEM-Style Constraints for PEFT with Dual Gradient Projection in LoRA
Brian Tekmen, Jason Yin, Qianqian Tong
Full fine-tuning of Large Language Models (LLMs) is computationally costly, motivating Continual Learning (CL) approaches that utilize parameter-efficient adapters. We revisit Grad…
LLM-Powered AI Agent Systems and Their Applications in Industry
Guannan Liang, Qianqian Tong
The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered agents offer greater flexibility…
Stochastic Variance-Reduced Iterative Hard Thresholding in Graph Sparsity Optimization
Derek Fox, Samuel Hernandez, Qianqian Tong
Stochastic optimization algorithms are widely used for large-scale data analysis due to their low per-iteration costs, but they often suffer from slow asymptotic convergence caused…
Escaping Saddle Points with Stochastically Controlled Stochastic Gradient Methods
Guannan Liang, Qianqian Tong, Chunjiang Zhu +1
Stochastically controlled stochastic gradient (SCSG) methods have been proved to converge efficiently to first-order stationary points which, however, can be saddle points in nonco…
Federated Nonconvex Sparse Learning
Qianqian Tong, Guannan Liang, Tan Zhu +1
Nonconvex sparse learning plays an essential role in many areas, such as signal processing and deep network compression. Iterative hard thresholding (IHT) methods are the state-of-…
Asynchronous Parallel Stochastic Quasi-Newton Methods
Qianqian Tong, Guannan Liang, Xingyu Cai +2
Although first-order stochastic algorithms, such as stochastic gradient descent, have been the main force to scale up machine learning models, such as deep neural nets, the second-…
Effective Proximal Methods for Non-convex Non-smooth Regularized Learning
Guannan Liang, Qianqian Tong, Jiahao Ding +2
Sparse learning is a very important tool for mining useful information and patterns from high dimensional data. Non-convex non-smooth regularized learning problems play essential r…
Effective Federated Adaptive Gradient Methods with Non-IID Decentralized Data
Qianqian Tong, Guannan Liang, Jinbo Bi
Federated learning allows loads of edge computing devices to collaboratively learn a global model without data sharing. The analysis with partial device participation under non-IID…
Calibrating the Adaptive Learning Rate to Improve Convergence of ADAM
Qianqian Tong, Guannan Liang, Jinbo Bi
Adaptive gradient methods (AGMs) have become popular in optimizing the nonconvex problems in deep learning area. We revisit AGMs and identify that the adaptive learning rate (A-LR)…