Search Results for author: Dong Yin

Found 26 papers, 6 papers with code

Convolutional Neural Networks Trained to Identify Words Provide a Surprisingly Good Account of Visual Form Priming Effects

no code implementations8 Feb 2023 Dong Yin, Valerio Biscione, Jeffrey Bowers

A wide variety of orthographic coding schemes and models of visual word identification have been developed to account for masked priming data that provide a measure of orthographic similarity between letter strings.

Object Recognition

Architecture Matters in Continual Learning

no code implementations1 Feb 2022 Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Timothy Nguyen, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar

However, in this work, we show that the choice of architecture can significantly impact the continual learning performance, and different architectures lead to different trade-offs between the ability to remember previous tasks and learning new ones.

Continual Learning

Wide Neural Networks Forget Less Catastrophically

no code implementations21 Oct 2021 Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Huiyi Hu, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar

A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the distribution shifts.

Continual Learning

Morse-STF: Improved Protocols for Privacy-Preserving Machine Learning

no code implementations24 Sep 2021 Qizhi Zhang, Sijun Tan, Lichun Li, Yun Zhao, Dong Yin, Shan Yin

Finally, we introduce Morse-STF, an end-to-end privacy-preserving system for machine learning training that leverages all these improved protocols.

BIG-bench Machine Learning Privacy Preserving

Efficient Local Planning with Linear Function Approximation

no code implementations12 Aug 2021 Dong Yin, Botao Hao, Yasin Abbasi-Yadkori, Nevena Lazić, Csaba Szepesvári

Under the assumption that the Q-functions of all policies are linear in known features of the state-action pairs, we show that our algorithms have polynomial query and computational costs in the dimension of the features, the effective planning horizon, and the targeted sub-optimality, while these costs are independent of the size of the state space.

An Instance-Dependent Simulation Framework for Learning with Label Noise

1 code implementation23 Jul 2021 Keren Gu, Xander Masotto, Vandana Bachani, Balaji Lakshminarayanan, Jack Nikodem, Dong Yin

We propose a simulation framework for generating instance-dependent noisy labels via a pseudo-labeling paradigm.

Learning with noisy labels

Revisiting the Loss Weight Adjustment in Object Detection

1 code implementation17 Mar 2021 Wenxin Yu, Xueling Shen, Jiajie Hu, Dong Yin

However, classification loss always dominates the multi-task loss in anchor-based methods, hampering the consistent and balanced optimization of the tasks.

Classification General Classification +5

Improved Regret Bound and Experience Replay in Regularized Policy Iteration

no code implementations25 Feb 2021 Nevena Lazic, Dong Yin, Yasin Abbasi-Yadkori, Csaba Szepesvari

We first show that the regret analysis of the Politex algorithm (a version of regularized policy iteration) can be sharpened from $O(T^{3/4})$ to $O(\sqrt{T})$ under nearly identical assumptions, and instantiate the bound with linear function approximation.

Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint

no code implementations19 Jun 2020 Dong Yin, Mehrdad Farajtabar, Ang Li, Nir Levine, Alex Mott

This problem is often referred to as catastrophic forgetting, a key challenge in continual learning of neural networks.

Continual Learning

A maximum-entropy approach to off-policy evaluation in average-reward MDPs

no code implementations NeurIPS 2020 Nevena Lazic, Dong Yin, Mehrdad Farajtabar, Nir Levine, Dilan Gorur, Chris Harris, Dale Schuurmans

This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs).

Off-policy evaluation

A Strong Feature Representation for Siamese Network Tracker

no code implementations18 Jul 2019 Zhipeng Zhou, Rui Zhang, Dong Yin

Firstly, the modified pre-trained VGG16 network is fine-tuned as the backbone.

Object Tracking

Stochastic Gradient and Langevin Processes

no code implementations ICML 2020 Xiang Cheng, Dong Yin, Peter L. Bartlett, Michael. I. Jordan

We prove quantitative convergence rates at which discrete Langevin-like processes converge to the invariant distribution of a related stochastic differential equation.

Robust Federated Learning in a Heterogeneous Environment

no code implementations16 Jun 2019 Avishek Ghosh, Justin Hong, Dong Yin, Kannan Ramchandran

Then, leveraging the statistical model, we solve the robust heterogeneous Federated Learning problem \emph{optimally}; in particular our algorithm matches the lower bound on the estimation error in dimension and the number of data points.

Clustering Federated Learning

Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation

2 code implementations6 Jun 2019 Raphael Gontijo Lopes, Dong Yin, Ben Poole, Justin Gilmer, Ekin D. Cubuk

Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions.

Data Augmentation object-detection +1

Rademacher Complexity for Adversarially Robust Generalization

1 code implementation29 Oct 2018 Dong Yin, Kannan Ramchandran, Peter Bartlett

For binary linear classifiers, we prove tight bounds for the adversarial Rademacher complexity, and show that the adversarial Rademacher complexity is never smaller than its natural counterpart, and it has an unavoidable dimension dependence, unless the weight vector has bounded $\ell_1$ norm.

BIG-bench Machine Learning

Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning

no code implementations14 Jun 2018 Dong Yin, Yudong Chen, Kannan Ramchandran, Peter Bartlett

In this setting, the Byzantine machines may create fake local minima near a saddle point that is far away from any true local minimum, even when robust gradient estimators are used.

A framework with updateable joint images re-ranking for Person Re-identification

no code implementations8 Mar 2018 Mingyue Yuan, Dong Yin, Jingwen Ding, Yuhao Luo, Zhipeng Zhou, Chengfeng Zhu, Rui Zhang

In this paper, we propose a novel framework with rules of updating images for person re-identification in real-world surveillance system.

Person Re-Identification Re-Ranking

Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates

1 code implementation ICML 2018 Dong Yin, Yudong Chen, Kannan Ramchandran, Peter Bartlett

In particular, these algorithms are shown to achieve order-optimal statistical error rates for strongly convex losses.

Online Learning for Non-Stationary A/B Tests

no code implementations14 Feb 2018 Andrés Muñoz Medina, Sergei Vassilvitskii, Dong Yin

The rollout of new versions of a feature in modern applications is a manual multi-stage process, as the feature is released to ever larger groups of users, while its performance is carefully monitored.

Gradient Diversity: a Key Ingredient for Scalable Distributed Learning

no code implementations18 Jun 2017 Dong Yin, Ashwin Pananjady, Max Lam, Dimitris Papailiopoulos, Kannan Ramchandran, Peter Bartlett

It has been experimentally observed that distributed implementations of mini-batch stochastic gradient descent (SGD) algorithms exhibit speedup saturation and decaying generalization ability beyond a particular batch-size.

Quantization

Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks

no code implementations26 May 2016 Adam Charles, Dong Yin, Christopher Rozell

In most existing analyses, the short-term memory (STM) capacity results conclude that the ESN network size must scale linearly with the input size for unstructured inputs.

Sliding-Window Optimization on an Ambiguity-Clearness Graph for Multi-object Tracking

no code implementations28 Nov 2015 Qi Guo, Le Dan, Dong Yin, Xiangyang Ji

Multi-object tracking remains challenging due to frequent occurrence of occlusions and outliers.

Multi-Object Tracking

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