Search Results for author: Chenxi Yang

Found 10 papers, 2 papers with code

A Practical Cross-Layer Approach for ML-Driven Storage Placement in Warehouse-Scale Computers

no code implementations10 Jan 2025 Chenxi Yang, Yan Li, Martin Maas, Mustafa Uysal, Ubaid Ullah Hafeez, Arif Merchant, Richard McDougall

Studying this problem in the context of real-world hyperscale data center deployments at Google, we identify a number of challenges that we believe cause this lack of practical adoption.

Scheduling

C3: Learning Congestion Controllers with Formal Certificates

no code implementations14 Dec 2024 Chenxi Yang, Divyanshu Saxena, Rohit Dwivedula, Kshiteej Mahajan, Swarat Chaudhuri, Aditya Akella

Learning-based congestion controllers offer better adaptability compared to traditional heuristic algorithms.

Beyond Score Changes: Adversarial Attack on No-Reference Image Quality Assessment from Two Perspectives

no code implementations20 Apr 2024 Chenxi Yang, Yujia Liu, Dingquan Li, Yan Zhong, Tingting Jiang

Meanwhile, it is important to note that the correlation, like ranking correlation, plays a significant role in NR-IQA tasks.

Adversarial Attack NR-IQA

LTL-Constrained Policy Optimization with Cycle Experience Replay

no code implementations17 Apr 2024 Ameesh Shah, Cameron Voloshin, Chenxi Yang, Abhinav Verma, Swarat Chaudhuri, Sanjit A. Seshia

In this work, we present Cycle Experience Replay (CyclER), a reward-shaping approach to this problem that allows continuous state and action spaces and the use of function approximations.

continuous-control Continuous Control +1

Defense Against Adversarial Attacks on No-Reference Image Quality Models with Gradient Norm Regularization

1 code implementation CVPR 2024 Yujia Liu, Chenxi Yang, Dingquan Li, Jianhao Ding, Tingting Jiang

To be specific, we present theoretical evidence showing that the magnitude of score changes is related to the $\ell_1$ norm of the model's gradient with respect to the input image.

Adversarial Robustness

Exploring Vulnerabilities of No-Reference Image Quality Assessment Models: A Query-Based Black-Box Method

no code implementations10 Jan 2024 Chenxi Yang, Yujia Liu, Dingquan Li, Tingting Jiang

Ensuring the robustness of NR-IQA methods is vital for reliable comparisons of different image processing techniques and consistent user experiences in recommendations.

NR-IQA

Adaptive Scheduling for Edge-Assisted DNN Serving

no code implementations19 Apr 2023 Jian He, Chenxi Yang, Zhaoyuan He, Ghufran Baig, Lili Qiu

Based on this observation, we first design a novel scheduling algorithm to exploit the batching benefits of all requests that run the same DNN.

Scheduling

Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation

no code implementations26 Jan 2023 Chenxi Yang, Greg Anderson, Swarat Chaudhuri

In each learning iteration, it uses the current version of this model and an external abstract interpreter to construct a differentiable signal for provable robustness.

Adversarial Robustness MuJoCo +3

Safe Neurosymbolic Learning with Differentiable Symbolic Execution

2 code implementations NeurIPS Workshop AIPLANS 2021 Chenxi Yang, Swarat Chaudhuri

We study the problem of learning worst-case-safe parameters for programs that use neural networks as well as symbolic, human-written code.

Cannot find the paper you are looking for? You can Submit a new open access paper.