arXiv research

CRIMED optimizes regret in bandits with unbounded stochastic corruption.

New algorithm robust to outliers in Bayesian Optimization.

Efficient algorithm detects communities in noisy graphs with robustness.

We study the problem of robust linear regression with response variable corruptions. We consider the oblivious adversary model, where the adversary corrupts a fraction of the responses in complete ignorance of the data. We provide a nearly linear time estimator which consistently estimates the true regression vector, e…

We consider the problem of unconstrained online convex optimization (OCO) with sub-exponential noise, a strictly more general problem than the standard OCO. In this setting, the learner receives a subgradient of the loss functions corrupted by sub-exponential noise and strives to achieve optimal regret guarantee, witho…

Density ratio estimation is a vital tool in both machine learning and statistical community. However, due to the unbounded nature of density ratio, the estimation procedure can be vulnerable to corrupted data points, which often pushes the estimated ratio toward infinity. In this paper, we present a robust estimator wh…

Paper develops proper, lower-bounded losses for weakly supervised classification.

Efficiently estimates linear models robust to corrupted data.

We prove several fundamental statistical bounds for entropic OT with the squared Euclidean cost between subgaussian probability measures in arbitrary dimension. First, through a new sample complexity result we establish the rate of convergence of entropic OT for empirical measures. Our analysis improves exponentially o…

We discuss a Pareto macro-economy (a) in a closed system with fixed total wealth and (b) in an open system with average mean wealth and compare our results to a similar analysis in a super-open system (c) with unbounded wealth. Wealth condensation takes place in the social phase for closed and open economies, while it …

Develops a comprehensive theory of corruption in supervised learning.

New algorithm robust to label corruptions in active learning.

Study finds corruption negatively impacts firm performance.

Study improves image classifier robustness to random p-norm corruptions.

Unified framework for corruption-robust linear bandits with optimal gap-dependent misspecification bounds.

We report quantitative relations between corruption level and economic factors, such as country wealth and foreign investment per capita, which are characterized by a power law spanning multiple scales of wealth and investments per capita. These relations hold for diverse countries, and also remain stable over differen…

CUTS removes corruption from models without clean data, improving utility and security.

Study robust estimation under varying corruption probabilities in data.

Two new algorithms improve performance in adversarial bandits with unbounded losses.

Binary classification improves with a small fraction of corrupted labels.

Constructs unbounded Kasparov product for sphere embeddings into Euclidean space.

Unbounded convex domains have zero mean curvature on disconnected boundaries.

We study the problem of corrupted sensing, a generalization of compressed sensing in which one aims to recover a signal from a collection of corrupted or unreliable measurements. While an arbitrary signal cannot be recovered in the face of arbitrary corruption, tractable recovery is possible when both signal and corrup…

New algorithm optimizes noisy, potentially corrupted functions.

New algorithm reduces linear contextual bandit regret with adversarial corruption.

We extend the model of stochastic bandits with adversarial corruption (Lykouriset al., 2018) to the stochastic linear optimization problem (Dani et al., 2008). Our algorithm is agnostic to the amount of corruption chosen by the adaptive adversary. The regret of the algorithm only increases linearly in the amount of cor…

Robust algorithm optimizes corrupted Gaussian process bandits.

Picket guards against corrupted data in machine learning models.

We use methods from network science to analyze corruption risk in a large administrative dataset of over 4 million public procurement contracts from European Union member states covering the years 2008-2016. By mapping procurement markets as bipartite networks of issuers and winners of contracts we can visualize and de…

New method for contextual bandits with corrupted context.

The paper proves homotopy equivalences for spaces of unbounded Fredholm operators.

Estimates GLMs robustly against label corruptions.

Algorithm maximizes total reward in multi-agent bandits with adversarial corruptions.

The main purpose of this paper is to formalize the modelling process, analysis and mathematical definition of corruption when entering into a contract between principal agent and producers. The formulation of the problem and the definition of concepts for the general case are considered. For definiteness, all calculati…

New algorithm robustly trains deep neural networks under corrupted supervision.

Golden L surface has unbounded bunching of saddle connections

We inspect a possible clustering structure of the corruption perception among 134 countries. Using the average linkage clustering, we uncover a well-defined hierarchy in the relationships among countries. Four main clusters are identified and they suggest that countries worldwide can be quite well separated according t…

This study tackles adversarial corruption in model-based reinforcement learning.

Current reinforcement learning methods fail if the reward function is imperfect, i.e. if the agent observes reward different from what it actually receives. We study this problem within the formalism of Corrupt Reward Markov Decision Processes (CRMDPs). We show that if the reward corruption in a CRMDP is sufficiently "…

Improved SGD for robust linear and ReLU regression with adversarial corruptions.

This memoir presents a systematic study of the utility maximization problem of an investor in a constrained and unbounded financial market. Building upon the work of Hu et al. (2005) [Ann. Appl. Probab., 15, 1691--1712] in a bounded framework, we extend our analysis to the more challenging unbounded case. Our methodolo…

Monotone adversarial corruptions degrade optimal learning algorithms.

Study robust mean estimation under coordinate-level corruptions using Hamming distance.

It is shown that the compactly supported identity component of the diffeomorphism group of the 2-dimensional punctured torus $\mathbb T^2_p$ is an unbounded group. It follows that the fragmentation norm of $\mathbb T^2_p$ is unbounded.

New inequalities for unbounded functions improve denoising score matching.

Conventional sampling techniques fall short of drawing descriptive sketches of the data when the data is grossly corrupted as such corruptions break the low rank structure required for them to perform satisfactorily. In this paper, we present new sampling algorithms which can locate the informative columns in presence …

Adversarial training improves robustness against common corruptions.

Adaptive learning method identifies and corrects corrupted data.