11 citations · 25 across the 14 of their papers we have counts for
17 papers
Stability is Stable: Connections between Replicability, Privacy, and Adaptive Generalization
Mark Bun, Marco Gaboardi, Max Hopkins +5
The notion of replicable algorithms was introduced in Impagliazzo et al. [STOC '22] to describe randomized algorithms that are stable under the resampling of their inputs. More pre…
Do PAC-Learners Learn the Marginal Distribution?
Max Hopkins, Daniel M. Kane, Shachar Lovett +1
The Fundamental Theorem of PAC Learning asserts that learnability of a concept class is equivalent to the of empirical error in to its mean,…
Robust Empirical Risk Minimization with Tolerance
Robi Bhattacharjee, Max Hopkins, Akash Kumar +2
Developing simple, sample-efficient learning algorithms for robust classification is a pressing issue in today's tech-dominated world, and current theoretical techniques requiring…
Eigenstripping, Spectral Decay, and Edge-Expansion on Posets
Jason Gaitonde, Max Hopkins, Tali Kaufman +2
We study the relationship between the underlying structure of posets and the spectral and combinatorial properties of their higher-order random walks. While fast mixing of random w…
Explicit Lower Bounds Against -Rounds of Sum-of-Squares
Max Hopkins, Ting-Chun Lin
We construct an explicit family of 3-XOR instances hard for -levels of the Sum-of-Squares (SoS) semi-definite programming hierarchy. Not only is this the first explicit const…
Sampling Equilibria: Fast No-Regret Learning in Structured Games
Daniel Beaglehole, Max Hopkins, Daniel Kane +2
Learning and equilibrium computation in games are fundamental problems across computer science and economics, with applications ranging from politics to machine learning. Much of t…
Active Learning Polynomial Threshold Functions
Omri Ben-Eliezer, Max Hopkins, Chutong Yang +1
We initiate the study of active learning polynomial threshold functions (PTFs). While traditional lower bounds imply that even univariate quadratics cannot be non-trivially activel…
Hypercontractivity on High Dimensional Expanders: a Local-to-Global Approach for Higher Moments
Mitali Bafna, Max Hopkins, Tali Kaufman +1
Hypercontractivity is one of the most powerful tools in Boolean function analysis. Originally studied over the discrete hypercube, recent years have seen increasing interest in ext…
Realizable Learning is All You Need
Max Hopkins, Daniel M. Kane, Shachar Lovett +1
The equivalence of realizable and agnostic learnability is a fundamental phenomenon in learning theory. With variants ranging from classical settings like PAC learning and regressi…
Bounded Memory Active Learning through Enriched Queries
Max Hopkins, Daniel Kane, Shachar Lovett +1
The explosive growth of easily-accessible unlabeled data has lead to growing interest in active learning, a paradigm in which data-hungry learning algorithms adaptively select info…
High Dimensional Expanders: Eigenstripping, Pseudorandomness, and Unique Games
Mitali Bafna, Max Hopkins, Tali Kaufman +1
Higher order random walks (HD-walks) on high dimensional expanders (HDX) have seen an incredible amount of study and application since their introduction by Kaufman and Mass [KM16]…
Point Location and Active Learning: Learning Halfspaces Almost Optimally
Max Hopkins, Daniel M. Kane, Shachar Lovett +1
Given a finite set and a binary linear classifier , how many queries of the form are required to learn the label of eve…
Noise-tolerant, Reliable Active Classification with Comparison Queries
Max Hopkins, Daniel Kane, Shachar Lovett +1
With the explosion of massive, widely available unlabeled data in the past years, finding label and time efficient, robust learning algorithms has become ever more important in the…
A Novel CMB Component Separation Method: Hierarchical Generalized Morphological Component Analysis
Sebastian Wagner-Carena, Max Hopkins, Ana Diaz Rivero +1
We present a novel technique for Cosmic Microwave Background (CMB) foreground subtraction based on the framework of blind source separation. Inspired by previous work incorporating…
The Power of Comparisons for Actively Learning Linear Classifiers
Max Hopkins, Daniel M. Kane, Shachar Lovett
In the world of big data, large but costly to label datasets dominate many fields. Active learning, a semi-supervised alternative to the standard PAC-learning model, was introduced…
Doppelgangers: the Ur-Operation and Posets of Bounded Height
Thomas Browning, Max Hopkins, Zander Kelley
In the early 1970's, Richard Stanley and Kenneth Johnson introduced and laid the groundwork for studying the order polynomial of partially ordered sets (posets). Decades later, Ham…
Simulated Annealing for JPEG Quantization
Max Hopkins, Michael Mitzenmacher, Sebastian Wagner-Carena
JPEG is one of the most widely used image formats, but in some ways remains surprisingly unoptimized, perhaps because some natural optimizations would go outside the standard that…