REVIEW 17 cited by
Certifying Some Distributional Robustness with Principled Adversarial Training
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Certifying Some Distributional Robustness with Principled Adversarial Training
read the original abstract
Neural networks are vulnerable to adversarial examples and researchers have proposed many heuristic attack and defense mechanisms. We address this problem through the principled lens of distributionally robust optimization, which guarantees performance under adversarial input perturbations. By considering a Lagrangian penalty formulation of perturbing the underlying data distribution in a Wasserstein ball, we provide a training procedure that augments model parameter updates with worst-case perturbations of training data. For smooth losses, our procedure provably achieves moderate levels of robustness with little computational or statistical cost relative to empirical risk minimization. Furthermore, our statistical guarantees allow us to efficiently certify robustness for the population loss. For imperceptible perturbations, our method matches or outperforms heuristic approaches.
Forward citations
Cited by 17 Pith papers
-
A Single-Loop Regularized Newton Method for Nonconvex-Strongly-Concave Minimax Optimization
A single-loop regularized Newton method matches O(ε^{-1.5}) global complexity and adds local superlinear rate for deterministic nonconvex-strongly-concave minimax problems while improving stochastic complexities by O(...
-
Lipschitz Optimization for Formal Verification of Homographies
Formal verification method using Lipschitz optimization on homographies to certify vision network robustness to camera pose changes in predominantly planar scenes.
-
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
Asymmetric Langevin Unlearning uses public data to suppress unlearning noise costs by O(1/n_pub²), enabling practical mass unlearning with preserved utility under distribution mismatch.
-
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
ALU uses public data to suppress unlearning cost quadratically while characterizing distribution mismatch effects, enabling mass unlearning with maintained utility.
-
Amnesia: A Stealthy Replay Attack on Continual Learning Dreams
Amnesia is a replay composition attack on continual learning that tilts class distributions under visibility (delta) and mass (f) budgets to reduce accuracy while evading audits.
-
Reinforcement Learning Disrupts Gradient-Based Adversarial Optimization
RL training disrupts gradient-based adversarial attacks by inducing unstable low-magnitude gradients that limit the effectiveness of methods like PGD within practical budgets.
-
Distributionally Robust Multi-Objective Optimization
DR-MOO adds distributional robustness to multi-objective optimization and gives single-loop MGDA algorithms reaching epsilon-Pareto-stationary points in O(epsilon^{-4}) samples for nonconvex problems.
-
Robust Representation Learning through Explicit Environment Modeling
Explicitly modeling and marginalizing environment variation via generalized random-intercept models produces representations that support robust average prediction across unseen environments and outperform invariant-l...
-
A Distributionally Robust Reinforcement Learning Framework for Constrained Urban EV Dispatch
A robust semi-Markov RL agent with MILP feasibility projection and Wasserstein ambiguity set achieves $1.22M net profit on an NYC EV simulator with zero feeder violations, outperforming heuristic and other RL baselines.
-
Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization
RIA uses adversarial exploration of counterfactual graph environments via label-invariant augmentations to improve OoD generalization in graph classification tasks.
-
Multivariate Time Series Data Imputation via Distributionally Robust Regularization
DRIO adds worst-case Wasserstein regularization to time series imputation, yielding a tractable adversarial surrogate and alternating algorithm that improves robustness under missingness.
-
A first-order method for nonconvex-nonconcave minimax problems under a local Kurdyka-Lojasiewicz condition
An inexact proximal gradient algorithm with complexity bounds for finding approximate stationary points in minimax problems under local varying KL conditions on the inner problem.
-
A Distributionally Robust Reinforcement Learning Framework for Constrained Urban EV Dispatch
PD-RSAC, a distributionally robust SAC variant with GCN encoder and MILP constraint projection, reports $1.22M net profit on an NYC taxi-based EV simulator while achieving zero feeder violations, outperforming heurist...
-
Robust SGLD algorithm for solving non-convex distributionally robust optimisation problems
Develops robust SGLD with non-asymptotic convergence bounds for non-convex DRO and applies it to neural network regression under adversarial corruption.
-
Generative models for decision-making under distributional shift
Generative models via pushforward maps, Fokker-Planck equations, and Wasserstein geometry enable learning nominal uncertainty, stressed distributions for robustness, and conditional posteriors under distributional shift.
-
Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
A tutorial framing deep learning as a complement to optimization for sequential decision-making under uncertainty, with applications in supply chains, healthcare, and energy.
-
Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
Offline RL promises to extract high-utility policies from static datasets but faces fundamental challenges that current methods only partially address.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.