Search Results for author:
Found 11 papers, 0 papers with code
Stability is Stable: Connections between Replicability, Privacy, and Adaptive Generalization
In particular, we give sample-efficient algorithmic reductions between perfect generalization, approximate differential privacy, and replicability for a broad class of statistical problems.
Do PAC-Learners Learn the Marginal Distribution?
We study a foundational variant of Valiant and Vapnik and Chervonenkis' Probably Approximately Correct (PAC)-Learning in which the adversary is restricted to a known family of marginal distributions $\mathscr{P}$.
Robust Empirical Risk Minimization with Tolerance
Developing simple, sample-efficient learning algorithms for robust classification is a pressing issue in today's tech-dominated world, and current theoretical techniques requiring exponential sample complexity and complicated improper learning rules fall far from answering the need.
Active Learning Polynomial Threshold Functions
We initiate the study of active learning polynomial threshold functions (PTFs).
Realizable Learning is All You Need
The equivalence of realizable and agnostic learnability is a fundamental phenomenon in learning theory.
Bounded Memory Active Learning through Enriched Queries
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 informative examples in order to lower prohibitively expensive labeling costs.
Point Location and Active Learning: Learning Halfspaces Almost Optimally
Given a finite set $X \subset \mathbb{R}^d$ and a binary linear classifier $c: \mathbb{R}^d \to \{0, 1\}$, how many queries of the form $c(x)$ are required to learn the label of every point in $X$?
Noise-tolerant, Reliable Active Classification with Comparison Queries
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 theory and in practice.
A Novel CMB Component Separation Method: Hierarchical Generalized Morphological Component Analysis
We present a novel technique for Cosmic Microwave Background (CMB) foreground subtraction based on the framework of blind source separation.
The Power of Comparisons for Actively Learning Linear Classifiers
While previous results show that active learning performs no better than its supervised alternative for important concept classes such as linear separators, we show that by adding weak distributional assumptions and allowing comparison queries, active learning requires exponentially fewer samples.
Simulated Annealing for JPEG Quantization
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 defines JPEG.
