Search Results for author:
Found 23 papers, 3 papers with code
Exact Recovery Guarantees for Parameterized Non-linear System Identification Problem under Adversarial Attacks
In this work, we study the system identification problem for parameterized non-linear systems using basis functions under adversarial attacks.
A CMDP-within-online framework for Meta-Safe Reinforcement Learning
Meta-reinforcement learning has widely been used as a learning-to-learn framework to solve unseen tasks with limited experience.
Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses
Matrix sensing problems exhibit pervasive non-convexity, plaguing optimization with a proliferation of suboptimal spurious solutions.
Exact Recovery for System Identification with More Corrupt Data than Clean Data
We highlight that the attack vectors are allowed to be correlated with each other in this work, whereas we make some assumptions about the times at which the attacks happen.
Over-parametrization via Lifting for Low-rank Matrix Sensing: Conversion of Spurious Solutions to Strict Saddle Points
This paper studies the role of over-parametrization in solving non-convex optimization problems.
Scalable Multi-Agent Reinforcement Learning with General Utilities
The objective is to find a localized policy that maximizes the average of the team's local utility functions without the full observability of each agent in the team.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Non-stationary Risk-sensitive Reinforcement Learning: Near-optimal Dynamic Regret, Adaptive Detection, and Separation Design
We study risk-sensitive reinforcement learning (RL) based on an entropic risk measure in episodic non-stationary Markov decision processes (MDPs).
Learning of Dynamical Systems under Adversarial Attacks -- Null Space Property Perspective
We study the identification of a linear time-invariant dynamical system affected by large-and-sparse disturbances modeling adversarial attacks or faults.
Semidefinite Programming versus Burer-Monteiro Factorization for Matrix Sensing
In this paper, we shed light on some major differences between these two methods.
Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction
In the exact setting, we prove an $O(T^{-1/3})$ convergence rate for both the average optimality gap and constraint violation, which further improves to $O(T^{-1/2})$ under strong concavity of the objective in the occupancy measure.
Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints
We consider primal-dual-based reinforcement learning (RL) in episodic constrained Markov decision processes (CMDPs) with non-stationary objectives and constraints, which plays a central role in ensuring the safety of RL in time-varying environments.
Stochastic $L^\natural$-convex Function Minimization
When applied to a stochastic submodular function, the computational complexity of the proposed algorithms is lower than that of the existing stochastic submodular minimization algorithms.
On the Global Optimum Convergence of Momentum-based Policy Gradient
For the generic Fisher-non-degenerate policy parametrizations, our result is the first single-loop and finite-batch PG algorithm achieving $\tilde{O}(\epsilon^{-3})$ global optimality sample complexity.
Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization
Our result is the first global convergence and sample complexity results for the stochastic entropy-regularized vanilla PG method.
Factorization Approach for Low-complexity Matrix Completion Problems: Exponential Number of Spurious Solutions and Failure of Gradient Methods
It is well-known that the Burer-Monteiro (B-M) factorization approach can efficiently solve low-rank matrix optimization problems under the RIP condition.
A Dual Approach to Constrained Markov Decision Processes with Entropy Regularization
We study entropy-regularized constrained Markov decision processes (CMDPs) under the soft-max parameterization, in which an agent aims to maximize the entropy-regularized value function while satisfying constraints on the expected total utility.
Sharp Restricted Isometry Property Bounds for Low-rank Matrix Recovery Problems with Corrupted Measurements
By analyzing the landscape of the non-convex problem, we first propose a global guarantee on the maximum distance between an arbitrary local minimizer and the ground truth under the assumption that the RIP constant is smaller than $1/2$.
When Does MAML Objective Have Benign Landscape?
The paper studies the complexity of the optimization problem behind the Model-Agnostic Meta-Learning (MAML) algorithm.
Large-Scale Traffic Signal Offset Optimization
The offset optimization problem seeks to coordinate and synchronize the timing of traffic signals throughout a network in order to enhance traffic flow and reduce stops and delays.
Optimization and Control Systems and Control Systems and Control
Sharp Restricted Isometry Bounds for the Inexistence of Spurious Local Minima in Nonconvex Matrix Recovery
Using the technique, we prove that in the case of a rank-1 ground truth, an RIP constant of $\delta<1/2$ is both necessary and sufficient for exact recovery from any arbitrary initial point (such as a random point).
Stability-certified reinforcement learning: A control-theoretic perspective
We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems.
How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery?
When the linear measurements of an instance of low-rank matrix recovery satisfy a restricted isometry property (RIP)---i. e. they are approximately norm-preserving---the problem is known to contain no spurious local minima, so exact recovery is guaranteed.
Sparse Semidefinite Programs with Guaranteed Near-Linear Time Complexity via Dualized Clique Tree Conversion
Clique tree conversion solves large-scale semidefinite programs by splitting an $n\times n$ matrix variable into up to $n$ smaller matrix variables, each representing a principal submatrix of up to $\omega\times\omega$.
Optimization and Control
