Learning Constant-Depth Circuits in Malicious Noise Models

• URL: http://arxiv.org/abs/2411.03570v1
• Date: Wed, 06 Nov 2024 00:19:58 GMT
• Title: Learning Constant-Depth Circuits in Malicious Noise Models
• Authors: Adam R. Klivans, Konstantinos Stavropoulos, Arsen Vasilyan,
• Abstract summary: We prove Linial, Mansour, and Nisan's quasipolynomial-time algorithm for learning constant-depth circuits. We attain the best possible dependence on the noise rate and succeed in the harshest possible noise model.
• Score: 9.036777309376697
• License:
• Abstract: The seminal work of Linial, Mansour, and Nisan gave a quasipolynomial-time algorithm for learning constant-depth circuits ($\mathsf{AC}^0$) with respect to the uniform distribution on the hypercube. Extending their algorithm to the setting of malicious noise, where both covariates and labels can be adversarially corrupted, has remained open. Here we achieve such a result, inspired by recent work on learning with distribution shift. Our running time essentially matches their algorithm, which is known to be optimal assuming various cryptographic primitives. Our proof uses a simple outlier-removal method combined with Braverman's theorem for fooling constant-depth circuits. We attain the best possible dependence on the noise rate and succeed in the harshest possible noise model (i.e., contamination or so-called "nasty noise").

Related papers

• Already Moderate Population Sizes Provably Yield Strong Robustness to Noise [53.27802701790209]
  We show that two evolutionary algorithms can tolerate constant noise probabilities without increasing the runtime on the OneMax benchmark. Our results are based on a novel proof argument that the noiseless offspring can be seen as a biased uniform crossover between the parent and the noisy offspring.
  arXiv  Detail & Related papers  (2024-04-02T16:35:52Z)
• Super Non-singular Decompositions of Polynomials and their Application to Robustly Learning Low-degree PTFs [39.468324211376505]
  We study the efficient learnability of low-degree threshold functions (PTFs) in the presence of a constant fraction of adversarial corruptions. Our algorithm employs an iterative approach inspired by localization techniques previously used in the context of learning linear threshold functions.
  arXiv  Detail & Related papers  (2024-03-31T02:03:35Z)
• Scalable noisy quantum circuits for biased-noise qubits [37.69303106863453]
  We consider biased-noise qubits affected only by bit-flip errors, which is motivated by existing systems of stabilized cat qubits. For realistic noise models, phase-flip will not be negligible, but in the Pauli-Twirling approximation, we show that our benchmark could check the correctness of circuits containing up to $106$ gates.
  arXiv  Detail & Related papers  (2023-05-03T11:27:50Z)
• Certified Adversarial Robustness Within Multiple Perturbation Bounds [38.3813286696956]
  Randomized smoothing (RS) is a well known certified defense against adversarial attacks. In this work, we aim to improve the certified adversarial robustness against multiple perturbation bounds simultaneously.
  arXiv  Detail & Related papers  (2023-04-20T16:42:44Z)
• A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Bandits [118.22458816174144]
  We propose a novel robust elimination-type algorithm that runs in epochs, combines exploration with infrequent switching to select a small subset of actions, and plays each action for multiple time instants. Our algorithm, GP Robust Phased Elimination (RGP-PE), successfully balances robustness to corruptions with exploration and exploitation. We perform the first empirical study of robustness in the corrupted GP bandit setting, and show that our algorithm is robust against a variety of adversarial attacks.
  arXiv  Detail & Related papers  (2022-02-03T21:19:36Z)
• Breaking the Moments Condition Barrier: No-Regret Algorithm for Bandits with Super Heavy-Tailed Payoffs [27.636407641546914]
  We propose a novel robust statistical estimator, mean of medians, which estimates a random variable by computing the empirical mean of a sequence of empirical medians. We show that the regret bound is near-optimal even with very heavy-tailed noise.
  arXiv  Detail & Related papers  (2021-10-26T17:30:44Z)
• Plug-And-Play Learned Gaussian-mixture Approximate Message Passing [71.74028918819046]
  We propose a plug-and-play compressed sensing (CS) recovery algorithm suitable for any i.i.d. source prior. Our algorithm builds upon Borgerding's learned AMP (LAMP), yet significantly improves it by adopting a universal denoising function within the algorithm. Numerical evaluation shows that the L-GM-AMP algorithm achieves state-of-the-art performance without any knowledge of the source prior.
  arXiv  Detail & Related papers  (2020-11-18T16:40:45Z)
• A Polynomial Time Algorithm for Learning Halfspaces with Tsybakov Noise [55.45544638410858]
  We study the problem of PAC learning homogeneous halfspaces in the presence of Tsybakov noise. Our algorithm learns the true halfspace within any accuracy $epsilon$.
  arXiv  Detail & Related papers  (2020-10-04T22:19:06Z)
• Learning Halfspaces with Tsybakov Noise [50.659479930171585]
  We study the learnability of halfspaces in the presence of Tsybakov noise. We give an algorithm that achieves misclassification error $epsilon$ with respect to the true halfspace.
  arXiv  Detail & Related papers  (2020-06-11T14:25:02Z)
• TAdam: A Robust Stochastic Gradient Optimizer [6.973803123972298]
  Machine learning algorithms aim to find patterns from observations, which may include some noise, especially in robotics domain. To perform well even with such noise, we expect them to be able to detect outliers and discard them when needed. We propose a new gradient optimization method, whose robustness is directly built in the algorithm, using the robust student-t distribution as its core idea.
  arXiv  Detail & Related papers  (2020-02-29T04:32:36Z)
• Learning with Differentiable Perturbed Optimizers [54.351317101356614]
  We propose a systematic method to transform operations into operations that are differentiable and never locally constant. Our approach relies on perturbeds, and can be used readily together with existing solvers. We show how this framework can be connected to a family of losses developed in structured prediction, and give theoretical guarantees for their use in learning tasks.
  arXiv  Detail & Related papers  (2020-02-20T11:11:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.