Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

13263952 · Jun 202019922001200920172026
48 results for corruption tolerance

We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic to the level of adversarial contamination and can tolerate a significant amount…

2019-02-22abs ↗pdf ↗

Robust estimation is much more challenging in high dimensions than it is in one dimension: Most techniques either lead to intractable optimization problems or estimators that can tolerate only a tiny fraction of errors. Recent work in theoretical computer science has shown that, in appropriate distributional models, it…

2017-03-02abs ↗pdf ↗

We consider the problem of optimizing an unknown (typically non-convex) function with a bounded norm in some Reproducing Kernel Hilbert Space (RKHS), based on noisy bandit feedback. We consider a novel variant of this problem in which the point evaluations are not only corrupted by random noise, but also adversarial co…

2020-03-04abs ↗pdf ↗

Develops a robust GMM estimator for outlier-tolerant inference.

problem Sensitive GMM estimation to outliers in inference problems.
method Robustified GMM estimator with computational efficiency and recovery guarantees.
result First computationally efficient GMM estimator for εε fraction of adversarial outliers with O(ε)O(\sqrtε) recovery guarantee.

Efficient algorithm detects communities in noisy graphs with robustness.

problem Community detection in stochastic block models with adversarial corruptions.
method Efficient algorithm using semidefinite programming for robust clustering.
result Achieves error O(ε)+eC2(1±o(1))O(ε) + e^{-\frac{C}{2} (1 \pm o(1))} for εε-fraction of corruptions.

Given full or partial information about a collection of points that lie close to a union of several subspaces, subspace clustering refers to the process of clustering the points according to their subspace and identifying the subspaces. One popular approach, sparse subspace clustering (SSC), represents each sample as a…

2017-07-08abs ↗pdf ↗

A robust loss for anomaly mitigation and unsupervised contamination classification

problem Detecting and mitigating contamination in supervised and unsupervised settings
method Neural Bayesian Anomaly Mitigation (NBAM)
result Recovering the structure of contamination and identifying label-flip pairs

New methods for handling time-varying label noise in time series classification.

problem Temporal label noise in time series classification tasks.
method Proposed methods to estimate temporal label noise function directly from data.
result Our methods lead to state-of-the-art performance under diverse types of temporal label noise.

We consider high dimensional sparse regression, and develop strategies able to deal with arbitrary -- possibly, severe or coordinated -- errors in the covariance matrix XX. These may come from corrupted data, persistent experimental errors, or malicious respondents in surveys/recommender systems, etc. Such non-stochas…

2013-01-12abs ↗pdf ↗

Fault-tolerant federated learning for non-uniform data.

problem Faulty workers corrupting data in federated learning.
method Fault-resilient proximal gradient (FRPG) algorithm with Nesterov's acceleration and local FRPG for reduced communication.
result FRPG and LFRPG converge faster than robust stochastic aggregation.

DFMR improves robustness of learning finite mixture models in distributed settings.

problem Learning finite mixture models in distributed settings with Byzantine failures.
method DFMR leverages pairwise L2 distances to filter and retain local estimates, ensuring robust aggregation.
result DFMR achieves optimal convergence rate and asymptotic equivalence to global maximum likelihood estimate.

We study the problem of recovering an incomplete m×nm\times n matrix of rank rr with columns arriving online over time. This is known as the problem of life-long matrix completion, and is widely applied to recommendation system, computer vision, system identification, etc. The challenge is to design provable algorithms…

2016-12-01abs ↗pdf ↗

We consider the problem of Robust PCA in the fully and partially observed settings. Without corruptions, this is the well-known matrix completion problem. From a statistical standpoint this problem has been recently well-studied, and conditions on when recovery is possible (how many observations do we need, how many co…

2016-05-25abs ↗pdf ↗

Efficiently learns halfspaces with malicious noise, near-optimal label complexity.

problem Learning ss-sparse halfspaces under malicious label noise.
method Active learning algorithm with instance reweighting and empirical risk minimization.
result Near-optimal label complexity of O(slog4d/ε)O(s \log^4 d / ε) and noise tolerance Ω(ε)Ω(ε).

We introduce a differential geometric framework for describing families of quantum error-correcting codes and for understanding quantum fault tolerance. This work unifies the notion of topological fault tolerance with fault tolerance in other kinds of quantum error-correcting codes. In particular, we use fibre bundles …

2013-09-26abs ↗pdf ↗

Study examines how risk tolerance impacts long-term investment returns.

problem Understanding the impact of risk tolerance on investment returns over time.
method Used Malliavin calculus and Hansen--Scheinkman decomposition.
result Risk aversion affects long-term investment utility through eigenvalues and eigenfunctions.

FastSecAgg improves federated learning security and efficiency.

problem Privacy leakage in federated learning due to model parameter sharing.
method Introduces FastSecAgg, a secure aggregation protocol with FFT-based multi-secret sharing (FastShare).
result Efficient in computation and communication, robust to client dropouts.

We analyze the adversarial examples problem in terms of a model's fault tolerance with respect to its input. Whereas previous work focuses on arbitrarily strict threat models, i.e., εε-perturbations, we consider arbitrary valid inputs and propose an information-based characteristic for evaluating tolerance to diverse …

2018-11-30abs ↗pdf ↗

Fault-tolerant neural networks inspired by biological error correction codes.

problem Achieving reliable computation with unreliable neurons.
method Using biological error correction codes from grid cells in the mammalian cortex to develop a fault-tolerant neural network.
result Noisy biological neurons operate below a fault-tolerance threshold, suggesting a mechanism for reliable computation in the brain.

Paper addresses fault-tolerance in distributed machine learning with stochastic gradient descent.

problem Fault-tolerance in distributed stochastic gradient descent (D-SGD) for machine learning.
method Proposes norm-based comparative gradient elimination (CGE) to robustify D-SGD against Byzantine faulty agents.
result CGE guarantees fault-tolerance against a bounded fraction of Byzantine agents under standard stochastic assumptions.

Asynchronous distributed machine learning solutions have proven very effective so far, but always assuming perfectly functioning workers. In practice, some of the workers can however exhibit Byzantine behavior, caused by hardware failures, software bugs, corrupt data, or even malicious attacks. We introduce \emph{Karda…

2018-02-22abs ↗pdf ↗

Develops a comprehensive theory of corruption in supervised learning.

problem Widespread corruption in data collection affects supervised learning problems.
method Introduces a general theory of corruption using Markov kernels, distinguishing and comparing corruption types.
result Establishes a unified framework for corruption types and develops mitigation strategies.

New algorithm robust to label corruptions in active learning.

problem Active learning under unknown adversarial label corruptions.
method Proposed a new active learning algorithm that is provably correct without assumptions on corruptions.
result Achieves minimax label complexity in non-corrupted setting and only requires additional labels to achieve desired accuracy in corrupted setting.

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

problem Improving robustness of image classifiers to real-world imperceptible corruptions.
method Training and testing with random p-norm corruptions, evaluating robustness against different p-norms.
result Training with a combination of p-norm corruptions significantly improves robustness.

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

problem Effective learning in linear bandits with corrupted rewards across different corruption models.
method Unified framework for analyzing strong and weak corruption, connection to gap-dependent misspecification, and specialized algorithm.
result Optimal bounds for gap-dependent misspecification in linear bandits.

Gradient codes adapt to varying straggler counts in distributed learning.

problem Mitigating slow worker nodes (stragglers) in distributed machine learning.
method Proposes a flexible gradient coding scheme that concatenates codes for different straggler tolerances, adapting to actual straggler counts.
result Significantly lower latency compared to fixed-tolerance gradient codes.

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…

2007-05-01abs ↗pdf ↗

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

problem Removing corruption from models without access to clean training data.
method CUTS uses a proxy set to amplify corruption and subtract it from model weights.
result CUTS recovers a large fraction of lost utility and nearly eliminates attacks with minimal damage.

The study examines robust decision-making in volatile financial markets, finding action robustness is more impactful than uncertainty tolerance.

problem Sequential decision making in high-frequency markets under evolving uncertainty.
method Analyzes two dimensions of robustness: uncertainty tolerance and action robustness, using simulations and empirical evidence.
result Action robustness has a larger impact on profitability than uncertainty tolerance, and excessive robustness can reduce profitability in illiquid markets.

Binary classification improves with a small fraction of corrupted labels.

problem Binary classification with corrupted labels.
method Established corruption as a form of regularization and computed upper bounds on estimation error.
result Corruption is beneficial only up to a small fraction of the total sample, scaling with the square root of the sample size.

The study formalizes temporal precision and recall for anomaly detection in sequences.

problem Insufficient understanding of precision and recall in sequential anomaly detection.
method Formalized temporal precision and recall measures, developed time-tolerant confusion matrices, and demonstrated statistical significance.
result Precision and recall may overestimate performance with temporal tolerance.