Search Results for author: Shaolei Ren

Found 30 papers, 11 papers with code

CAFE: Carbon-Aware Federated Learning in Geographically Distributed Data Centers

no code implementations6 Nov 2023 Jieming Bian, Lei Wang, Shaolei Ren, Jie Xu

Training large-scale artificial intelligence (AI) models demands significant computational power and energy, leading to increased carbon footprint with potential environmental repercussions.

Federated Learning

Towards Environmentally Equitable AI via Geographical Load Balancing

1 code implementation20 Jun 2023 Pengfei Li, Jianyi Yang, Adam Wierman, Shaolei Ren

The results demonstrate that existing GLB approaches may amplify environmental inequity while our proposed equity-aware GLB can significantly reduce the regional disparity in terms of carbon and water footprints.

Learning-Augmented Decentralized Online Convex Optimization in Networks

no code implementations16 Jun 2023 Pengfei Li, Jianyi Yang, Adam Wierman, Shaolei Ren

This paper studies decentralized online convex optimization in a networked multi-agent system and proposes a novel algorithm, Learning-Augmented Decentralized Online optimization (LADO), for individual agents to select actions only based on local online information.

Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees

1 code implementation31 May 2023 Pengfei Li, Jianyi Yang, Shaolei Ren

The key novelty of LOMAR is a new online switching operation which, based on a judicious condition to hedge against future uncertainties, decides whether to follow the expert's decision or the RL decision for each online item.

Reinforcement Learning (RL)

Robustified Learning for Online Optimization with Memory Costs

no code implementations1 May 2023 Pengfei Li, Jianyi Yang, Shaolei Ren

In this paper, we propose a novel expert-robustified learning (ERL) approach, achieving {both} good average performance and robustness.

Scheduling

NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation

1 code implementation28 Apr 2023 Tong Zhou, Yukui Luo, Shaolei Ren, Xiaolin Xu

In this work, we propose an active model IP protection scheme, namely NNSplitter, which actively protects the model by splitting it into two parts: the obfuscated model that performs poorly due to weight obfuscation, and the model secrets consisting of the indexes and original values of the obfuscated weights, which can only be accessed by authorized users with the support of the trusted execution environment.

Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models

1 code implementation6 Apr 2023 Pengfei Li, Jianyi Yang, Mohammad A. Islam, Shaolei Ren

To respond to the global water challenges, AI models can, and also must, take social responsibility and lead by example by addressing their own water footprint.

MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption

1 code implementation23 Feb 2023 Yejia Liu, Shijin Duan, Xiaolin Xu, Shaolei Ren

Fast model updates for unseen tasks on intelligent edge devices are crucial but also challenging due to the limited computational power.

Meta-Learning

Learning-Assisted Algorithm Unrolling for Online Optimization with Budget Constraints

no code implementations3 Dec 2022 Jianyi Yang, Shaolei Ren

Online optimization with multiple budget constraints is challenging since the online decisions over a short time horizon are coupled together by strict inventory constraints.

Rolling Shutter Correction

Navigating Memory Construction by Global Pseudo-Task Simulation for Continual Learning

1 code implementation16 Oct 2022 Yejia Liu, Wang Zhu, Shaolei Ren

To provide an approximate solution to this problem in the online continual learning setting, we further propose the Global Pseudo-task Simulation (GPS), which mimics future catastrophic forgetting of the current task by permutation.

Combinatorial Optimization Continual Learning

ObfuNAS: A Neural Architecture Search-based DNN Obfuscation Approach

1 code implementation17 Aug 2022 Tong Zhou, Shaolei Ren, Xiaolin Xu

Nonetheless, we observe that, with only extracting an obfuscated DNN architecture, the adversary can still retrain a substitute model with high performance (e. g., accuracy), rendering the obfuscation techniques ineffective.

Neural Architecture Search

Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity

no code implementations2 Jul 2022 Jianyi Yang, Shaolei Ren

Based on the theoretical analysis, we propose a generalized informed training objective to better exploit the benefits of knowledge and balance the label and knowledge imperfectness, which is validated by the population risk bound.

Expert-Calibrated Learning for Online Optimization with Switching Costs

no code implementations18 Apr 2022 Pengfei Li, Jianyi Yang, Shaolei Ren

Nonetheless, by using the standard practice of training an ML model as a standalone optimizer and plugging it into an ML-augmented algorithm, the average cost performance can be highly unsatisfactory.

A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural Accelerators

1 code implementation25 Mar 2022 Bingqian Lu, Zheyu Yan, Yiyu Shi, Shaolei Ren

We first perform neural architecture search to obtain a small set of optimal architectures for one accelerator candidate.

Neural Architecture Search

LeHDC: Learning-Based Hyperdimensional Computing Classifier

1 code implementation18 Mar 2022 Shijin Duan, Yejia Liu, Shaolei Ren, Xiaolin Xu

Thanks to the tiny storage and efficient execution, hyperdimensional Computing (HDC) is emerging as a lightweight learning framework on resource-constrained hardware.

A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices

1 code implementation9 Mar 2022 Shijin Duan, Xiaolin Xu, Shaolei Ren

Nonetheless, they have two fundamental drawbacks, heuristic training process and ultra-high dimension, which result in sub-optimal inference accuracy and large model sizes beyond the capability of tiny devices with stringent resource constraints.

Learning for Robust Combinatorial Optimization: Algorithm and Application

no code implementations20 Dec 2021 Zhihui Shao, Jianyi Yang, Cong Shen, Shaolei Ren

Learning to optimize (L2O) has recently emerged as a promising approach to solving optimization problems by exploiting the strong prediction power of neural networks and offering lower runtime complexity than conventional solvers.

Combinatorial Optimization Edge-computing

Automated Customization of On-Thing Inference for Quality-of-Experience Enhancement

no code implementations11 Dec 2021 Yang Bai, Lixing Chen, Shaolei Ren, Jie Xu

The core of our method is a DNN selection module that learns user QoE patterns on-the-fly and identifies the best-fit DNN for on-thing inference with the learned knowledge.

Transfer Learning

One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search

1 code implementation1 Nov 2021 Bingqian Lu, Jianyi Yang, Weiwen Jiang, Yiyu Shi, Shaolei Ren

A key requirement of efficient hardware-aware NAS is the fast evaluation of inference latencies in order to rank different architectures.

Hardware Aware Neural Architecture Search Neural Architecture Search

Robust Bandit Learning with Imperfect Context

no code implementations9 Feb 2021 Jianyi Yang, Shaolei Ren

A standard assumption in contextual multi-arm bandit is that the true context is perfectly known before arm selection.

Management

Distributed Thompson Sampling

no code implementations3 Dec 2020 Jing Dong, Tan Li, Shaolei Ren, Linqi Song

To further improve the performance of distributed Thompson Sampling, we propose a distributed Elimination based Thompson Sampling algorithm that allow the agents to learn collaboratively.

Multi-Armed Bandits Thompson Sampling

A Quantitative Perspective on Values of Domain Knowledge for Machine Learning

no code implementations17 Nov 2020 Jianyi Yang, Shaolei Ren

With the exploding popularity of machine learning, domain knowledge in various forms has been playing a crucial role in improving the learning performance, especially when training data is limited.

BIG-bench Machine Learning

Scaling Up Deep Neural Network Optimization for Edge Inference

no code implementations1 Sep 2020 Bingqian Lu, Jianyi Yang, Shaolei Ren

In the first approach, we reuse the performance predictors built on a proxy device, and leverage the performance monotonicity to scale up the DNN optimization without re-building performance predictors for each different device.

Quantization

Increasing Trustworthiness of Deep Neural Networks via Accuracy Monitoring

no code implementations3 Jul 2020 Zhihui Shao, Jianyi Yang, Shaolei Ren

In this paper, we address trustworthiness of DNNs by using post-hoc processing to monitor the true inference accuracy on a user's dataset.

Image Classification Traffic Sign Detection

Calibrating Deep Neural Network Classifiers on Out-of-Distribution Datasets

no code implementations16 Jun 2020 Zhihui Shao, Jianyi Yang, Shaolei Ren

In this paper, we propose a new post-hoc confidence calibration method, called CCAC (Confidence Calibration with an Auxiliary Class), for DNN classifiers on OOD datasets.

Adversarial Attacks on Brain-Inspired Hyperdimensional Computing-Based Classifiers

no code implementations10 Jun 2020 Fangfang Yang, Shaolei Ren

Being an emerging class of in-memory computing architecture, brain-inspired hyperdimensional computing (HDC) mimics brain cognition and leverages random hypervectors (i. e., vectors with a dimensionality of thousands or even more) to represent features and to perform classification tasks.

General Classification

A Note on Latency Variability of Deep Neural Networks for Mobile Inference

no code implementations29 Feb 2020 Luting Yang, Bingqian Lu, Shaolei Ren

Running deep neural network (DNN) inference on mobile devices, i. e., mobile inference, has become a growing trend, making inference less dependent on network connections and keeping private data locally.

Spatio-temporal Edge Service Placement: A Bandit Learning Approach

no code implementations7 Oct 2018 Lixing Chen, Jie Xu, Shaolei Ren, Pan Zhou

To solve this problem and optimize the edge computing performance, we propose SEEN, a Spatial-temporal Edge sErvice placemeNt algorithm.

Decision Making Edge-computing

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