Search Results for author:
Found 27 papers, 0 papers with code
Distributed Dual Coordinate Ascent with Imbalanced Data on a General Tree Network
In this paper, we investigate the impact of imbalanced data on the convergence of distributed dual coordinate ascent in a tree network for solving an empirical loss minimization problem in distributed machine learning.
Minimax Optimal $Q$ Learning with Nearest Neighbors
A modification of the original $Q$ learning method was proposed in (Shah and Xie, 2018), which estimates $Q$ values with nearest neighbors.
Efficient Action Robust Reinforcement Learning with Probabilistic Policy Execution Uncertainty
Robust reinforcement learning (RL) aims to find a policy that optimizes the worst-case performance in the face of uncertainties.
Fairness-aware Regression Robust to Adversarial Attacks
In this paper, we take a first step towards answering the question of how to design fair machine learning algorithms that are robust to adversarial attacks.
Efficiently Escaping Saddle Points in Bilevel Optimization
Moreover, we propose an inexact NEgative-curvature-Originated-from-Noise Algorithm (iNEON), a pure first-order algorithm that can escape saddle point and find local minimum of stochastic bilevel optimization.
Efficient Action Poisoning Attacks on Linear Contextual Bandits
We show that, in both white-box and black-box settings, the proposed attack schemes can force the LinUCB agent to pull a target arm very frequently by spending only logarithm cost.
Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning
In this paper, we introduce a new class of attacks named action poisoning attacks, where an adversary can change the action signal selected by the agent.
On the Convergence of Projected Alternating Maximization for Equitable and Optimal Transport
This paper studies the equitable and optimal transport (EOT) problem, which has many applications such as fair division problems and optimal transport with multiple agents etc.
Optimal Stochastic Nonconvex Optimization with Bandit Feedback
In this paper, we analyze the continuous armed bandit problems for nonconvex cost functions under certain smoothness and sublevel set assumptions.
Projection Robust Wasserstein Barycenters
One of the popular solution methods for this task is to compute the barycenter of the probability measures under the Wasserstein metric.
A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance
We show that the complexity of arithmetic operations for RBCD to obtain an $\epsilon$-stationary point is $O(\epsilon^{-3})$.
On the Adversarial Robustness of LASSO Based Feature Selection
We formulate the modification strategy of the adversary as a bi-level optimization problem.
Analysis of KNN Density Estimation
We show that kNN density estimation is minimax optimal under both $\ell_1$ and $\ell_\infty$ criteria, if the support set is known.
Robust Low-rank Matrix Completion via an Alternating Manifold Proximal Gradient Continuation Method
This problem aims to decompose a partially observed matrix into the superposition of a low-rank matrix and a sparse matrix, where the sparse matrix captures the grossly corrupted entries of the matrix.
Optimal Feature Manipulation Attacks Against Linear Regression
In this paper, we investigate how to manipulate the coefficients obtained via linear regression by adding carefully designed poisoning data points to the dataset or modify the original data points.
Minimax Optimal Estimation of KL Divergence for Continuous Distributions
Estimating Kullback-Leibler divergence from identical and independently distributed samples is an important problem in various domains.
Action-Manipulation Attacks Against Stochastic Bandits: Attacks and Defense
To defend against this class of attacks, we introduce a novel algorithm that is robust to action-manipulation attacks when an upper bound for the total attack cost is given.
Minimax Rate Optimal Adaptive Nearest Neighbor Classification and Regression
For both classification and regression problems, existing works have shown that, if the distribution of the feature vector has bounded support and the probability density function is bounded away from zero in its support, the convergence rate of the standard kNN method, in which k is the same for all test samples, is minimax optimal.
On the Adversarial Robustness of Subspace Learning
We first characterize the optimal rank-one attack strategy that maximizes the subspace distance between the subspace learned from the original data matrix and that learned from the modified data matrix.
On the Adversarial Robustness of Multivariate Robust Estimation
In this paper, we investigate the adversarial robustness of multivariate $M$-Estimators.
How did Donald Trump Surprisingly Win the 2016 United States Presidential Election? an Information-Theoretic Perspective (Clean Sensing for Big Data Analytics:Optimal Strategies,Estimation Error Bounds Tighter than the Cramér-Rao Bound)
In this paper, we study the inaccuracies of opinion polls in the 2016 election through the lens of information theory.
Quick Best Action Identification in Linear Bandit Problems
In the considered best action identification problem, instead of minimizing the accumulative regret as done in existing works, the learner aims to obtain an accurate estimate of the underlying parameter based on his action and reward sequences.
Analysis of KNN Information Estimators for Smooth Distributions
Existing work has analyzed the convergence rate of this estimator for random variables whose densities are bounded away from zero in its support.
Distributed Dual Coordinate Ascent in General Tree Networks and Communication Network Effect on Synchronous Machine Learning
Additionally, we show that adapting number of local and global iterations to network communication delays in the distributed dual coordinated ascent algorithm can improve its convergence speed.
On Randomized Distributed Coordinate Descent with Quantized Updates
In this paper, we study the randomized distributed coordinate descent algorithm with quantized updates.
Precise Phase Transition of Total Variation Minimization
Characterizing the phase transitions of convex optimizations in recovering structured signals or data is of central importance in compressed sensing, machine learning and statistics.
Are Slepian-Wolf Rates Necessary for Distributed Parameter Estimation?
We consider a distributed parameter estimation problem, in which multiple terminals send messages related to their local observations using limited rates to a fusion center who will obtain an estimate of a parameter related to observations of all terminals.
