Search Results for author:
Found 34 papers, 9 papers with code
Speeding Up Distributed Machine Learning Using Codes
We focus on two of the most basic building blocks of distributed learning algorithms: matrix multiplication and data shuffling.
Coded Computation over Heterogeneous Clusters
There have been recent results that demonstrate the impact of coding for efficient utilization of computation and storage redundancy to alleviate the effect of stragglers and communication bottlenecks in homogeneous clusters.
Distributed, Parallel, and Cluster Computing Information Theory Information Theory
Sparsity-based Defense against Adversarial Attacks on Linear Classifiers
In this paper, we study this phenomenon in the setting of a linear classifier, and show that it is possible to exploit sparsity in natural data to combat $\ell_{\infty}$-bounded adversarial perturbations.
Combating Adversarial Attacks Using Sparse Representations
It is by now well-known that small adversarial perturbations can induce classification errors in deep neural networks (DNNs).
An Exact Quantized Decentralized Gradient Descent Algorithm
We consider the problem of decentralized consensus optimization, where the sum of $n$ smooth and strongly convex functions are minimized over $n$ distributed agents that form a connected network.
Robust Adversarial Learning via Sparsifying Front Ends
We also devise attacks based on the locally linear model that outperform the well-known FGSM attack.
CodedReduce: A Fast and Robust Framework for Gradient Aggregation in Distributed Learning
That is, it parallelizes the communications over a tree topology leading to efficient bandwidth utilization, and carefully designs a redundant data set allocation and coding strategy at the nodes to make the proposed gradient aggregation scheme robust to stragglers.
Robust and Communication-Efficient Collaborative Learning
We consider a decentralized learning problem, where a set of computing nodes aim at solving a non-convex optimization problem collaboratively.
Sharp Guarantees for Solving Random Equations with One-Bit Information
We study the performance of a wide class of convex optimization-based estimators for recovering a signal from corrupted one-bit measurements in high-dimensions.
FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization
Federated learning is a distributed framework according to which a model is trained over a set of devices, while keeping data localized.
Sharp Asymptotics and Optimal Performance for Inference in Binary Models
We study convex empirical risk minimization for high-dimensional inference in binary models.
Polarizing Front Ends for Robust CNNs
The vulnerability of deep neural networks to small, adversarially designed perturbations can be attributed to their "excessive linearity."
Quantized Decentralized Stochastic Learning over Directed Graphs
We consider a decentralized stochastic learning problem where data points are distributed among computing nodes communicating over a directed graph.
Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions
For a stylized setting with Gaussian features and problem dimensions that grow large at a proportional rate, we start with sharp performance characterizations and then derive tight lower bounds on the estimation and prediction error that hold over a wide class of loss functions and for any value of the regularization parameter.
Robust Federated Learning: The Case of Affine Distribution Shifts
In such settings, the training data is often statistically heterogeneous and manifests various distribution shifts across users, which degrades the performance of the learnt model.
Asymptotic Behavior of Adversarial Training in Binary Classification
It has been consistently reported that many machine learning models are susceptible to adversarial attacks i. e., small additive adversarial perturbations applied to data points can cause misclassification.
Adversarially Robust Classification based on GLRT
We evaluate the GLRT approach for the special case of binary hypothesis testing in white Gaussian noise under $\ell_{\infty}$ norm-bounded adversarial perturbations, a setting for which a minimax strategy optimizing for the worst-case attack is known.
Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity
Federated Learning is a novel paradigm that involves learning from data samples distributed across a large network of clients while the data remains local.
Incentivizing Routing Choices for Safe and Efficient Transportation in the Face of the COVID-19 Pandemic
In turn, significant increases in traffic congestion are expected, since people are likely to prefer using their own vehicles or taxis as opposed to riskier and more crowded options such as the railway.
Robust Classification Under $\ell_0$ Attack for the Gaussian Mixture Model
Under the assumption that data is distributed according to the Gaussian mixture model, our goal is to characterize the optimal robust classifier and the corresponding robust classification error as well as a variety of trade-offs between robustness, accuracy, and the adversary's budget.
Incentivizing Efficient Equilibria in Traffic Networks with Mixed Autonomy
Traffic congestion has large economic and social costs.
Emergent Prosociality in Multi-Agent Games Through Gifting
Coordination is often critical to forming prosocial behaviors -- behaviors that increase the overall sum of rewards received by all agents in a multi-agent game.
Generalized Likelihood Ratio Test for Adversarially Robust Hypothesis Testing
We derive the worst-case attack for the GLRT defense, and show that its asymptotic performance (as the dimension of the data increases) approaches that of the minimax defense.
Efficient and Robust Classification for Sparse Attacks
In the past two decades we have seen the popularity of neural networks increase in conjunction with their classification accuracy.
Imitation Learning by Estimating Expertise of Demonstrators
In this work, we show that unsupervised learning over demonstrator expertise can lead to a consistent boost in the performance of imitation learning algorithms.
Binary Classification Under $\ell_0$ Attacks for General Noise Distribution
We introduce a classification method which employs a nonlinear component called truncation, and show in an asymptotic scenario, as long as the adversary is restricted to perturb no more than $\sqrt{d}$ data samples, we can almost achieve the optimal classification error in the absence of the adversary, i. e. we can completely neutralize adversary's effect.
Straggler-Resilient Personalized Federated Learning
Federated Learning is an emerging learning paradigm that allows training models from samples distributed across a large network of clients while respecting privacy and communication restrictions.
An Optimal Transport Approach to Personalized Federated Learning
In this paper, we focus on this problem and propose a novel personalized Federated Learning scheme based on Optimal Transport (FedOT) as a learning algorithm that learns the optimal transport maps for transferring data points to a common distribution as well as the prediction model under the applied transport map.
Equal Improvability: A New Fairness Notion Considering the Long-term Impact
In order to promote long-term fairness, we propose a new fairness notion called Equal Improvability (EI), which equalizes the potential acceptance rate of the rejected samples across different groups assuming a bounded level of effort will be spent by each rejected sample.
The Fair Value of Data Under Heterogeneous Privacy Constraints in Federated Learning
We also formulate a heterogeneous federated learning problem for the platform with privacy level options for users.
Pricing for Multi-modal Pickup and Delivery Problems with Heterogeneous Users
In this paper we study the pickup and delivery problem with multiple transportation modalities, and address the challenge of efficiently allocating transportation resources while price matching users with their desired delivery modes.
Inverse Reinforcement Learning by Estimating Expertise of Demonstrators
In Imitation Learning (IL), utilizing suboptimal and heterogeneous demonstrations presents a substantial challenge due to the varied nature of real-world data.
Learning to Understand: Identifying Interactions via the Mobius Transform
In the case where all interactions are between at most $t = \Theta(n^{\alpha})$ inputs, for $\alpha < 0. 409$, we are able to leverage results from group testing to provide the first algorithm that computes the Mobius transform in $O(Kt\log n)$ sample complexity and $O(K\mathrm{poly}(n))$ time with vanishing error as $K \rightarrow \infty$.
Generalization Properties of Adversarial Training for $\ell_0$-Bounded Adversarial Attacks
In this paper, we focus on the $\ell_0$-bounded adversarial attacks, and aim to theoretically characterize the performance of adversarial training for an important class of truncated classifiers.
