# Approximate resilience, monotonicity, and the complexity of agnostic learning

@inproceedings{DachmanSoled2015ApproximateRM,
title={Approximate resilience, monotonicity, and the complexity of agnostic learning},
author={Dana Dachman-Soled and Vitaly Feldman and Li-Yang Tan and Andrew Wan and Karl Wimmer},
booktitle={SODA},
year={2015}
}
• Dana Dachman-Soled, +2 authors Karl Wimmer
• Published in SODA 2015
• Computer Science, Mathematics
• A function $f$ is $d$-resilient if all its Fourier coefficients of degree at most $d$ are zero, i.e., $f$ is uncorrelated with all low-degree parities. We study the notion of $\mathit{approximate}$ $\mathit{resilience}$ of Boolean functions, where we say that $f$ is $\alpha$-approximately $d$-resilient if $f$ is $\alpha$-close to a $[-1,1]$-valued $d$-resilient function in $\ell_1$ distance. We show that approximate resilience essentially characterizes the complexity of agnostic learning of a… CONTINUE READING

#### Citations

##### Publications citing this paper.
SHOWING 1-10 OF 12 CITATIONS

## Tight Bounds on ℓ1 Approximation and Learning of Self-Bounding Functions

• Mathematics, Computer Science
• ALT
• 2017

## A General Characterization of the Statistical Query Complexity

VIEW 8 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

## Weighted Polynomial Approximations: Limits for Learning and Pseudorandomness

• Mathematics, Computer Science
• Electronic Colloquium on Computational Complexity
• 2014

## Tight Bounds on Low-Degree Spectral Concentration of Submodular and XOS Functions

• Mathematics, Computer Science
• 2015 IEEE 56th Annual Symposium on Foundations of Computer Science
• 2015

## On the Power of Learning from k-Wise Queries

• Computer Science, Mathematics
• ITCS
• 2017

## Pseudorandomness for read-k DNF formulas

• Computer Science
• SODA
• 2019

## Adaptivity Helps for Testing Juntas

• Mathematics, Computer Science
• Computational Complexity Conference
• 2015

## Depth without distress

VIEW 1 EXCERPT
CITES METHODS

## Fast agnostic classification

VIEW 2 EXCERPTS
CITES BACKGROUND

#### References

##### Publications referenced by this paper.
SHOWING 1-10 OF 48 REFERENCES

## Lower Bounds for Agnostic Learning via Approximate Rank

• Computer Science, Mathematics
• computational complexity
• 2010

## Randomly Supported Independence and Resistance

• Mathematics, Computer Science
• SIAM J. Comput.
• 2011

## Learning Monotone Decision Trees in Polynomial Time

• Mathematics, Computer Science
• SIAM J. Comput.
• 2007

## KKL, Kruskal-Katona, and Monotone Nets

• Computer Science, Mathematics
• SIAM J. Comput.
• 2013

## Unconditional lower bounds for learning intersections of halfspaces

• Computer Science, Mathematics
• Machine Learning
• 2007

## The bit extraction problem or t-resilient functions

• Benny Chor, +3 authors Roman Smolensky
• Mathematics, Computer Science
• 26th Annual Symposium on Foundations of Computer Science (sfcs 1985)
• 1985

## The Complexity of Learning Halfspaces using Generalized Linear Methods

• Computer Science, Mathematics
• COLT
• 2014

## Agnostic Learning of Monomials by Halfspaces Is Hard

• Mathematics, Computer Science
• 2009 50th Annual IEEE Symposium on Foundations of Computer Science
• 2009

## Finding Correlations in Subquadratic Time, with Applications to Learning Parities and Juntas

• Gregory Valiant
• Mathematics, Computer Science
• 2012 IEEE 53rd Annual Symposium on Foundations of Computer Science
• 2012