1 citations · 1 across the 16 of their papers we have counts for
22 papers
Learning Depth-3 Circuits with Polynomial Savings
Xi Chen, Animesh Fatehpuria, Shyamal Patel +1
We study the challenging problem of learning depth-three circuits in the mistake-bound model of (realizable) online learning, which is a more difficult model than distribution-free…
Distribution-Free Halfspace Testing with Samples
Xi Chen, Renato Ferreira Pinto, Nathaniel Harms +2
We prove a tight lower bound on the number of samples required for testing halfspaces over , in the distribution-free sample-based model where the underlying…
Sublinear-query relative-error testing of halfspaces
Xi Chen, Anindya De, Yizhi Huang +3
The relative-error property testing model was introduced in [CDHLNSY24] to facilitate the study of property testing for "sparse" Boolean-valued functions, i.e. ones for which only…
DNF formulas are efficiently testable with relative error
Xi Chen, William Pires, Toniann Pitassi +1
We give a poly-query algorithm for testing whether an unknown and arbitrary function is an -term DNF, in the challenging relative-error frame…
Testing noisy low-degree polynomials for sparsity
Yiqiao Bao, Anindya De, Shivam Nadimpalli +2
We consider the problem of testing whether an unknown low-degree polynomial over is sparse versus far from sparse, given access to noisy evaluations of the polyn…
Model-agnostic distribution recovery in high dimension via Fourier measurements
Xi Chen, Anindya De, Yizhi Huang +3
We study the problem of reconstructing an unknown probability distribution to high accuracy, given noisy information about its low-degree Fourier coefficients. Prior results for th…
Halfspaces are hard to test with relative error
Xi Chen, Anindya De, Yizhi Huang +3
Several recent works [DHLNSY25, CPPS25a, CPPS25b] have studied a model of property testing of Boolean functions under a \emph{relative-error} criterion. In this model, the distance…
Relative-error unateness testing
Xi Chen, Diptaksho Palit, Kabir Peshawaria +3
The model of relative-error property testing of Boolean functions has been the subject of significant recent research effort [CDH+24][CPPS25a][CPPS25b] In this paper we consider th…
Faster exact learning of k-term DNFs with membership and equivalence queries
Josh Alman, Shivam Nadimpalli, Shyamal Patel +1
In 1992 Blum and Rudich [BR92] gave an algorithm that uses membership and equivalence queries to learn -term DNF formulas over in time , improv…
DNF Learning via Locally Mixing Random Walks
Josh Alman, Shivam Nadimpalli, Shyamal Patel +1
We give two results on PAC learning DNF formulas using membership queries in the challenging "distribution-free" learning framework, where learning algorithms must succeed for an a…
A Mysterious Connection Between Tolerant Junta Testing and Agnostically Learning Conjunctions
Xi Chen, Shyamal Patel, Rocco A. Servedio
The main conceptual contribution of this paper is identifying a previously unnoticed connection between two central problems in computational learning theory and property testing:…
Testing Juntas and Junta Subclasses with Relative Error
Xi Chen, William Pires, Toniann Pitassi +1
This papers considers the junta testing problem in a recently introduced ``relative error'' variant of the standard Boolean function property testing model. In relative-error testi…
Relative-error testing of conjunctions and decision lists
Xi Chen, William Pires, Toniann Pitassi +1
We study the relative-error property testing model for Boolean functions that was recently introduced in the work of Chen et al. (SODA 2025). In relative-error testing, the testing…
Lower Bounds for Convexity Testing
Xi Chen, Anindya De, Shivam Nadimpalli +2
We consider the problem of testing whether an unknown and arbitrary set (given as a black-box membership oracle) is convex, versus -far from…
Relative-error monotonicity testing
Xi Chen, Anindya De, Yizhi Huang +4
The standard model of Boolean function property testing is not well suited for testing functions which have few satisfying assignments, since every such function…
Trace reconstruction from local statistical queries
Xi Chen, Anindya De, Chin Ho Lee +1
The goal of trace reconstruction is to reconstruct an unknown -bit string given only independent random traces of , where a random trace of is obtained by passing …
Testing Sumsets is Hard
Xi Chen, Shivam Nadimpalli, Tim Randolph +2
A subset of the Boolean hypercube is a sumset if for some . Sumsets are central objects of study in add…
Detecting Low-Degree Truncation
Anindya De, Huan Li, Shivam Nadimpalli +1
We consider the following basic, and very broad, statistical problem: Given a known high-dimensional distribution over and a collection of data points in…
Testing Intersecting and Union-Closed Families
Xi Chen, Anindya De, Yuhao Li +2
Inspired by the classic problem of Boolean function monotonicity testing, we investigate the testability of other well-studied properties of combinatorial finite set systems, speci…
Gaussian Approximation of Convex Sets by Intersections of Halfspaces
Anindya De, Shivam Nadimpalli, Rocco A. Servedio
We study the approximability of general convex sets in by intersections of halfspaces, where the approximation quality is measured with respect to the standard Gauss…
Efficient deterministic approximate counting for low-degree polynomial threshold functions
Anindya De, Rocco Servedio
We give a deterministic algorithm for approximately counting satisfying assignments of a degree- polynomial threshold function (PTF). Given a degree- input polynomial $p(x_1,…
Learning -Modal Distributions via Testing
Constantinos Daskalakis, Ilias Diakonikolas, Rocco A. Servedio
A -modal probability distribution over the discrete domain is one whose histogram has at most "peaks" and "valleys." Such distributions are natural generalizat…