Search Results for author:
Found 50 papers, 8 papers with code
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.
Intent Demonstration in General-Sum Dynamic Games via Iterative Linear-Quadratic Approximations
Autonomous agents should be able to coordinate with other agents without knowing their intents ahead of time.
MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers
Adversarial robustness often comes at the cost of degraded accuracy, impeding the real-life application of robust classification models.
Let's Go Shopping (LGS) -- Web-Scale Image-Text Dataset for Visual Concept Understanding
Vision and vision-language applications of neural networks, such as image classification and captioning, rely on large-scale annotated datasets that require non-trivial data-collecting processes.
Mixing Classifiers to Alleviate the Accuracy-Robustness Trade-Off
However, standard learning models often suffer from an accuracy-robustness trade-off, which is a limitation that must be overcome in the control of safety-critical systems that require both high performance and rigorous robustness guarantees.
Tight Certified Robustness via Min-Max Representations of ReLU Neural Networks
The reliable deployment of neural networks in control systems requires rigorous robustness guarantees.
Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization
SCQ works like a differentiable convex optimization (DCO) layer: in the forward pass, we solve for the optimal convex combination of codebook vectors that quantize the inputs.
Projected Randomized Smoothing for Certified Adversarial Robustness
Randomized smoothing is the current state-of-the-art method for producing provably robust classifiers.
Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation
Diffusion models power a vast majority of text-to-audio (TTA) generation methods.
Ranked #10 on
Audio Generation
on AudioCaps
Initial State Interventions for Deconfounded Imitation Learning
Imitation learning suffers from causal confusion.
Scenario-Game ADMM: A Parallelized Scenario-Based Solver for Stochastic Noncooperative Games
To accommodate this, we decompose the approximated game into a set of smaller games with few constraints for each sampled scenario, and propose a decentralized, consensus-based ADMM algorithm to efficiently compute a generalized Nash equilibrium (GNE) of the approximated game.
Meta-Learning Parameterized First-Order Optimizers using Differentiable Convex Optimization
Conventional optimization methods in machine learning and controls rely heavily on first-order update rules.
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.
Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing
While prior research has proposed a plethora of methods that build neural classifiers robust against adversarial robustness, practitioners are still reluctant to adopt them due to their unacceptably severe clean accuracy penalties.
Ranked #1 on
Adversarial Robustness
on CIFAR-100
(using extra training data)
Distributed Optimal Control of Graph Symmetric Systems via Graph Filters
Designing distributed optimal controllers subject to communication constraints is a difficult problem unless structural assumptions are imposed on the underlying dynamics and information exchange structure, e. g., sparsity, delay, or spatial invariance.
LQR Control with Sparse Adversarial Disturbances
Under mild conditions, we show that the disturbance-aware policy converges to the blind online policy if the number of disturbances grows sublinearly in the time horizon.
Semidefinite Programming versus Burer-Monteiro Factorization for Matrix Sensing
In this paper, we shed light on some major differences between these two methods.
An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Models
In this discussion paper, we survey recent research surrounding robustness of machine learning models.
Infinite-Horizon Reach-Avoid Zero-Sum Games via Deep Reinforcement Learning
We address this problem by designing a new value function with a contracting Bellman backup, where the super-zero level set, i. e., the set of states where the value function is evaluated to be non-negative, recovers the reach-avoid set.
Noisy Low-rank Matrix Optimization: Geometry of Local Minima and Convergence Rate
We prove that as long as the RIP constant of the noiseless objective is less than $1/3$, any spurious local solution of the noisy optimization problem must be close to the ground truth solution.
Efficient Global Optimization of Two-layer ReLU Networks: Quadratic-time Algorithms and Adversarial Training
We apply the robust convex optimization theory to convex training and develop convex formulations that train ANNs robust to adversarial inputs.
Safe Reinforcement Learning with Chance-constrained Model Predictive Control
Real-world reinforcement learning (RL) problems often demand that agents behave safely by obeying a set of designed constraints.
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.
Node-Variant Graph Filters in Graph Neural Networks
We show that, by replacing nonlinear activation functions by NVGFs, frequency creation mechanisms can be designed or learned.
Practical Convex Formulation of Robust One-hidden-layer Neural Network Training
Recent work has shown that the training of a one-hidden-layer, scalar-output fully-connected ReLU neural network can be reformulated as a finite-dimensional convex program.
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 $1/2$.
Distributed Linear-Quadratic Control with Graph Neural Networks
Controlling network systems has become a problem of paramount importance.
Towards Optimal Branching of Linear and Semidefinite Relaxations for Neural Network Robustness Certification
We extend the analysis to the SDP, where the feasible set geometry is exploited to design a branching scheme that minimizes the worst-case SDP relaxation error.
Improving Fairness and Privacy in Selection Problems
In this work, we study the possibility of using a differentially private exponential mechanism as a post-processing step to improve both fairness and privacy of supervised learning models.
Graph Neural Networks for Distributed Linear-Quadratic Control
When considering a network system, this renders the optimal controller a centralized one.
A Sequential Framework Towards an Exact SDP Verification of Neural Networks
We analyze the performance of this sequential SDP method both theoretically and empirically, and show that it bridges the gap as the number of cuts increases.
Certifying Neural Network Robustness to Random Input Noise from Samples
Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings.
Data-Driven Certification of Neural Networks with Random Input Noise
Methods to certify the robustness of neural networks in the presence of input uncertainty are vital in safety-critical settings.
Implicit Graph Neural Networks
Graph Neural Networks (GNNs) are widely used deep learning models that learn meaningful representations from graph-structured data.
Tightened Convex Relaxations for Neural Network Robustness Certification
In this paper, we consider the problem of certifying the robustness of neural networks to perturbed and adversarial input data.
Spectral Graph Attention Network with Fast Eigen-approximation
In this paper, we first introduce the attention mechanism in the spectral domain of graphs and present Spectral Graph Attention Network (SpGAT) that learns representations for different frequency components regarding weighted filters and graph wavelets bases.
Power up! Robust Graph Convolutional Network based on Graph Powering
By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability.
Octave Graph Convolutional Network
Many variants of Graph Convolutional Networks (GCNs) for representation learning have been proposed recently and have achieved fruitful results in various domains.
Efficient Learning of Distributed Linear-Quadratic Controllers
In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems.
Global Optimality Guarantees for Nonconvex Unsupervised Video Segmentation
In this paper, we consider the problem of unsupervised video object segmentation via background subtraction.
Power up! Robust Graph Convolutional Network via Graph Powering
By challenging the classical graph Laplacian, we propose a new convolution operator that is provably robust in the spectral domain and is incorporated in the GCN architecture to improve expressivity and interpretability.
Learning Sparse Dynamical Systems from a Single Sample Trajectory
In particular, we show that the proposed estimator can correctly identify the sparsity pattern of the system matrices with high probability, provided that the length of the sample trajectory exceeds a threshold.
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).
Exact Guarantees on the Absence of Spurious Local Minima for Non-negative Rank-1 Robust Principal Component Analysis
In particular, it is shown that a constant fraction of the measurements could be grossly corrupted and yet they would not create any spurious local solution.
A Fog Robotic System for Dynamic Visual Servoing
We use the system to enable robust teleoperation of a dynamic self-balancing robot from the cloud.
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.
Sample Complexity of Sparse System Identification Problem
A by-product of this result is that the number of sample trajectories required for sparse system identification is significantly smaller than the dimension of the system.
Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion
The sparse inverse covariance estimation problem is commonly solved using an $\ell_{1}$-regularized Gaussian maximum likelihood estimator known as "graphical lasso", but its computational cost becomes prohibitive for large data sets.
Sparse Inverse Covariance Estimation for Chordal Structures
We have also derived a closed-form solution that is optimal when the thresholded sample covariance matrix has an acyclic structure.
Graphical Lasso and Thresholding: Equivalence and Closed-form Solutions
The objective of this paper is to compare the computationally-heavy GL technique with a numerically-cheap heuristic method that is based on simply thresholding the sample covariance matrix.
