no code implementations • 1 Jul 2024 • Gautam Chandrasekaran, Adam Klivans, Vasilis Kontonis, Raghu Meka, Konstantinos Stavropoulos

In traditional models of supervised learning, the goal of a learner -- given examples from an arbitrary joint distribution on $\mathbb{R}^d \times \{\pm 1\}$ -- is to output a hypothesis that is competitive (to within $\epsilon$) of the best fitting concept from some class.

no code implementations • 27 Jun 2024 • Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Raghu Meka, Chiyuan Zhang

We study the differentially private (DP) empirical risk minimization (ERM) problem under the semi-sensitive DP setting where only some features are sensitive.

no code implementations • 26 Jun 2024 • Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath, Raghu Meka

A core component present in many successful neural network architectures, is an MLP block of two fully connected layers with a non-linear activation in between.

no code implementations • 23 Feb 2024 • Jonathan Kelner, Frederic Koehler, Raghu Meka, Dhruv Rohatgi

It is well-known that the statistical performance of Lasso can suffer significantly when the covariates of interest have strong correlations.

no code implementations • 18 Oct 2023 • Yuanzhi Li, Raghu Meka, Rina Panigrahy, Kulin Shah

Deep networks typically learn concepts via classifiers, which involves setting up a model and training it via gradient descent to fit the concept-labeled data.

no code implementations • 8 May 2023 • Badih Ghazi, Pritish Kamath, Ravi Kumar, Raghu Meka, Pasin Manurangsi, Chiyuan Zhang

We introduce a new mechanism for stochastic convex optimization (SCO) with user-level differential privacy guarantees.

no code implementations • 20 Apr 2023 • Sitan Chen, Zehao Dou, Surbhi Goel, Adam R Klivans, Raghu Meka

We consider the well-studied problem of learning a linear combination of $k$ ReLU activations with respect to a Gaussian distribution on inputs in $d$ dimensions.

no code implementations • 5 Mar 2022 • Jonathan A. Kelner, Frederic Koehler, Raghu Meka, Dhruv Rohatgi

Surprisingly, at the heart of our lower bound is a new positive result in compressed sensing.

no code implementations • 10 Feb 2022 • Sitan Chen, Aravind Gollakota, Adam R. Klivans, Raghu Meka

We give superpolynomial statistical query (SQ) lower bounds for learning two-hidden-layer ReLU networks with respect to Gaussian inputs in the standard (noise-free) model.

no code implementations • ICLR 2022 • Sitan Chen, Jerry Li, Yuanzhi Li, Raghu Meka

Arguably the most fundamental question in the theory of generative adversarial networks (GANs) is to understand to what extent GANs can actually learn the underlying distribution.

no code implementations • NeurIPS 2021 • Sitan Chen, Adam Klivans, Raghu Meka

While the problem of PAC learning neural networks from samples has received considerable attention in recent years, in certain settings like model extraction attacks, it is reasonable to imagine having more than just the ability to observe random labeled examples.

no code implementations • 8 Nov 2021 • Sitan Chen, Adam R Klivans, Raghu Meka

In this work we give the first polynomial-time algorithm for learning arbitrary one hidden layer neural networks activations provided black-box access to the network.

no code implementations • 17 Jun 2021 • Jonathan Kelner, Frederic Koehler, Raghu Meka, Dhruv Rohatgi

First, we show that the preconditioned Lasso can solve a large class of sparse linear regression problems nearly optimally: it succeeds whenever the dependency structure of the covariates, in the sense of the Markov property, has low treewidth -- even if $\Sigma$ is highly ill-conditioned.

no code implementations • 28 Sep 2020 • Sitan Chen, Adam R. Klivans, Raghu Meka

These results provably cannot be obtained using gradient-based methods and give the first example of a class of efficiently learnable neural networks that gradient descent will fail to learn.

no code implementations • 28 Apr 2020 • Sitan Chen, Raghu Meka

We give an algorithm that learns the polynomial within accuracy $\epsilon$ with sample complexity that is roughly $N = O_{r, d}(n \log^2(1/\epsilon) (\log n)^d)$ and runtime $O_{r, d}(N n^2)$.

no code implementations • NeurIPS 2020 • Jonathan Kelner, Frederic Koehler, Raghu Meka, Ankur Moitra

While there are a variety of algorithms (e. g. Graphical Lasso, CLIME) that provably recover the graph structure with a logarithmic number of samples, they assume various conditions that require the precision matrix to be in some sense well-conditioned.

no code implementations • 8 Mar 2018 • Adam Klivans, Pravesh K. Kothari, Raghu Meka

We give the first polynomial-time algorithm for performing linear or polynomial regression resilient to adversarial corruptions in both examples and labels.

no code implementations • ICML 2018 • Surbhi Goel, Adam Klivans, Raghu Meka

We give the first provably efficient algorithm for learning a one hidden layer convolutional network with respect to a general class of (potentially overlapping) patches.

no code implementations • 20 Jun 2017 • Adam Klivans, Raghu Meka

Our main application is an algorithm for learning the structure of t-wise MRFs with nearly-optimal sample complexity (up to polynomial losses in necessary terms that depend on the weights) and running time that is $n^{O(t)}$.

no code implementations • 10 Feb 2014 • Moritz Hardt, Raghu Meka, Prasad Raghavendra, Benjamin Weitz

Matrix Completion is the problem of recovering an unknown real-valued low-rank matrix from a subsample of its entries.

no code implementations • NeurIPS 2009 • Raghu Meka, Prateek Jain, Inderjit S. Dhillon

In this paper, we propose a graph theoretic approach to matrix completion that solves the problem for more realistic sampling models.

1 code implementation • NeurIPS 2010 • Raghu Meka, Prateek Jain, Inderjit S. Dhillon

Minimizing the rank of a matrix subject to affine constraints is a fundamental problem with many important applications in machine learning and statistics.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.