23 citations · 39 across the 12 of their papers we have counts for
13 papers
Cost-Aware Contrastive Routing for LLMs
Reza Shirkavand, Shangqian Gao, Peiran Yu +1
We study cost-aware routing for large language models across diverse and dynamic pools of models. Existing approaches often overlook prompt-specific context, rely on expensive mode…
Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models
Reza Shirkavand, Peiran Yu, Shangqian Gao +3
Recent advances in diffusion generative models have yielded remarkable progress. While the quality of generated content continues to improve, these models have grown considerably i…
Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models
Alireza Ganjdanesh, Reza Shirkavand, Shangqian Gao +1
Text-to-image (T2I) diffusion models have demonstrated impressive image generation capabilities. Still, their computational intensity prohibits resource-constrained organizations f…
Jointly Training and Pruning CNNs via Learnable Agent Guidance and Alignment
Alireza Ganjdanesh, Shangqian Gao, Heng Huang
Structural model pruning is a prominent approach used for reducing the computational cost of Convolutional Neural Networks (CNNs) before their deployment on resource-constrained de…
Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch
Xidong Wu, Shangqian Gao, Zeyu Zhang +5
Current techniques for deep neural network (DNN) pruning often involve intricate multi-step processes that require domain-specific expertise, making their widespread adoption chall…
Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold
Alireza Ganjdanesh, Shangqian Gao, Hirad Alipanah +1
Generative Adversarial Networks (GANs) have shown remarkable success in modeling complex data distributions for image-to-image translation. Still, their high computational demands…
Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps
Alireza Ganjdanesh, Shangqian Gao, Heng Huang
Convolutional Neural Networks (CNNs) compression is crucial to deploying these models in edge devices with limited resources. Existing channel pruning algorithms for CNNs have achi…
Bregman Gradient Policy Optimization
Feihu Huang, Shangqian Gao, Heng Huang
In the paper, we design a novel Bregman gradient policy optimization framework for reinforcement learning based on Bregman divergences and momentum techniques. Specifically, we pro…
Gradient Descent Ascent for Minimax Problems on Riemannian Manifolds
Feihu Huang, Shangqian Gao
In the paper, we study a class of useful minimax problems on Riemanian manifolds and propose a class of effective Riemanian gradient-based methods to solve these minimax problems.…
Momentum-Based Policy Gradient Methods
Feihu Huang, Shangqian Gao, Jian Pei +1
In the paper, we propose a class of efficient momentum-based policy gradient methods for the model-free reinforcement learning, which use adaptive learning rates and do not require…
Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization
Feihu Huang, Shangqian Gao, Jian Pei +1
In the paper, we propose a class of accelerated zeroth-order and first-order momentum methods for both nonconvex mini-optimization and minimax-optimization. Specifically, we propos…
Nonconvex Zeroth-Order Stochastic ADMM Methods with Lower Function Query Complexity
Feihu Huang, Shangqian Gao, Jian Pei +1
Zeroth-order (a.k.a, derivative-free) methods are a class of effective optimization methods for solving complex machine learning problems, where gradients of the objective function…
Zeroth-Order Stochastic Alternating Direction Method of Multipliers for Nonconvex Nonsmooth Optimization
Feihu Huang, Shangqian Gao, Songcan Chen +1
Alternating direction method of multipliers (ADMM) is a popular optimization tool for the composite and constrained problems in machine learning. However, in many machine learning…