Search Results for author:
Found 44 papers, 10 papers with code
On the Power of Compressed Sensing with Generative Models
for compressed sensing from $L$-Lipschitz generative models $G$.
On the Power of Compressed Sensing with Generative Models
for compressed sensing from $L$-Lipschitz generative models $G$.
Spectral Guarantees for Adversarial Streaming PCA
(2) In the insertion-only model, a variant of Oja's algorithm gets $o(1)$ error for $R = O(\log n \log d)$.
Airship Formations for Animal Motion Capture and Behavior Analysis
Using UAVs for wildlife observation and motion capture offers manifold advantages for studying animals in the wild, especially grazing herds in open terrain.
Diffusion Posterior Sampling is Computationally Intractable
Diffusion models are a remarkably effective way of learning and sampling from a distribution $p(x)$.
Improved Sample Complexity Bounds for Diffusion Model Training
Diffusion models have become the most popular approach to deep generative modeling of images, largely due to their empirical performance and reliability.
Sharp Noisy Binary Search with Monotonic Probabilities
We revisit the noisy binary search model of Karp and Kleinberg, in which we have $n$ coins with unknown probabilities $p_i$ that we can flip.
A Competitive Algorithm for Agnostic Active Learning
For some hypothesis classes and input distributions, active agnostic learning needs exponentially fewer samples than passive learning; for other classes and distributions, it offers little to no improvement.
Finite-Sample Symmetric Mean Estimation with Fisher Information Rate
The mean of an unknown variance-$\sigma^2$ distribution $f$ can be estimated from $n$ samples with variance $\frac{\sigma^2}{n}$ and nearly corresponding subgaussian rate.
Accelerated Video Annotation driven by Deep Detector and Tracker
In this paper, we propose a new annotation method which leverages a combination of a learning-based detector (SSD) and a learning-based tracker (RE$^3$).
High-dimensional Location Estimation via Norm Concentration for Subgamma Vectors
In location estimation, we are given $n$ samples from a known distribution $f$ shifted by an unknown translation $\lambda$, and want to estimate $\lambda$ as precisely as possible.
Hardness and Algorithms for Robust and Sparse Optimization
We further show fine-grained hardness of robust regression through a reduction from the minimum-weight $k$-clique conjecture.
Sharp Constants in Uniformity Testing via the Huber Statistic
It is known that the optimal sample complexity to distinguish the uniform distribution on $m$ elements from any $\epsilon$-far distribution with $1-\delta$ probability is $n = \Theta\left(\frac{\sqrt{m \log (1/\delta)}}{\epsilon^2} + \frac{\log (1/\delta)}{\epsilon^2}\right)$, which is achieved by the empirical TV tester.
Finite-Sample Maximum Likelihood Estimation of Location
We consider 1-dimensional location estimation, where we estimate a parameter $\lambda$ from $n$ samples $\lambda + \eta_i$, with each $\eta_i$ drawn i. i. d.
Coresets for Data Discretization and Sine Wave Fitting
The goal (e. g., for anomaly detection) is to approximate the $n$ points received so far in $P$ by a single frequency $\sin$, e. g. $\min_{c\in C}cost(P, c)+\lambda(c)$, where $cost(P, c)=\sum_{i=1}^n \sin^2(\frac{2\pi}{N} p_ic)$, $C\subseteq [N]$ is a feasible set of solutions, and $\lambda$ is a given regularization function.
AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation
In this letter, we present a novel markerless 3D human motion capture (MoCap) system for unstructured, outdoor environments that uses a team of autonomous unmanned aerial vehicles (UAVs) with on-board RGB cameras and computation.
Robust Compressed Sensing MR Imaging with Deep Generative Priors
The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep generative priors can be powerful tools for solving inverse problems.
Robust Compressed Sensing MRI with Deep Generative Priors
The CSGM framework (Bora-Jalal-Price-Dimakis'17) has shown that deep generative priors can be powerful tools for solving inverse problems.
Fairness for Image Generation with Uncertain Sensitive Attributes
This motivates the introduction of definitions that allow algorithms to be \emph{oblivious} to the relevant groupings.
Instance-Optimal Compressed Sensing via Posterior Sampling
We characterize the measurement complexity of compressed sensing of signals drawn from a known prior distribution, even when the support of the prior is the entire space (rather than, say, sparse vectors).
L1 Regression with Lewis Weights Subsampling
We consider the problem of finding an approximate solution to $\ell_1$ regression while only observing a small number of labels.
Linear Bandit Algorithms with Sublinear Time Complexity
For sufficiently large $K$, our algorithms have sublinear per-step complexity and $\tilde O(\sqrt{T})$ regret.
Near-Optimal Learning of Tree-Structured Distributions by Chow-Liu
For a distribution $P$ on $\Sigma^n$ and a tree $T$ on $n$ nodes, we say $T$ is an $\varepsilon$-approximate tree for $P$ if there is a $T$-structured distribution $Q$ such that $D(P\;||\;Q)$ is at most $\varepsilon$ more than the best possible tree-structured distribution for $P$.
Compressed Sensing with Approximate Priors via Conditional Resampling
We characterize the measurement complexity of compressed sensing of signals drawn from a known prior distribution, even when the support of the prior is the entire space (rather than, say, sparse vectors).
Optimal Testing of Discrete Distributions with High Probability
To illustrate the generality of our methods, we give optimal algorithms for testing collections of distributions and testing closeness with unequal sized samples.
Lower Bounds for Compressed Sensing with Generative Models
Second, we show that generative models generalize sparsity as a representation of structure.
Outlier-Robust High-Dimensional Sparse Estimation via Iterative Filtering
Specifically, we focus on the fundamental problems of robust sparse mean estimation and robust sparse PCA.
Adversarial Examples from Cryptographic Pseudo-Random Generators
In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805. 10204) we argued that adversarial examples in machine learning might be due to an inherent computational hardness of the problem.
Compressed Sensing with Adversarial Sparse Noise via L1 Regression
We present a simple and effective algorithm for the problem of \emph{sparse robust linear regression}.
Compressed Sensing with Deep Image Prior and Learned Regularization
We propose a novel method for compressed sensing recovery using untrained deep generative models.
Adversarial examples from computational constraints
First we prove that, for a broad set of classification tasks, the mere existence of a robust classifier implies that it can be found by a possibly exponential-time algorithm with relatively few training examples.
AmbientGAN: Generative models from lossy measurements
Generative models provide a way to model structure in complex distributions and have been shown to be useful for many tasks of practical interest.
Stochastic Multi-armed Bandits in Constant Space
We consider the stochastic bandit problem in the sublinear space setting, where one cannot record the win-loss record for all $K$ arms.
Active Regression via Linear-Sample Sparsification
We present an approach that improves the sample complexity for a variety of curve fitting problems, including active learning for linear regression, polynomial regression, and continuous sparse Fourier transforms.
Robust polynomial regression up to the information theoretic limit
We consider the problem of robust polynomial regression, where one receives samples $(x_i, y_i)$ that are usually within $\sigma$ of a polynomial $y = p(x)$, but have a $\rho$ chance of being arbitrary adversarial outliers.
Optimal Identity Testing with High Probability
Our new upper and lower bounds show that the optimal sample complexity of identity testing is \[ \Theta\left( \frac{1}{\epsilon^2}\left(\sqrt{n \log(1/\delta)} + \log(1/\delta) \right)\right) \] for any $n, \varepsilon$, and $\delta$.
Fast Regression with an $\ell_\infty$ Guarantee
Our main result is that, when $S$ is the subsampled randomized Fourier/Hadamard transform, the error $x' - x^*$ behaves as if it lies in a "random" direction within this bound: for any fixed direction $a\in \mathbb{R}^d$, we have with $1 - d^{-c}$ probability that \[ \langle a, x'-x^*\rangle \lesssim \frac{\|a\|_2\|x'-x^*\|_2}{d^{\frac{1}{2}-\gamma}}, \quad (1) \] where $c, \gamma > 0$ are arbitrary constants.
Compressed Sensing using Generative Models
The goal of compressed sensing is to estimate a vector from an underdetermined system of noisy linear measurements, by making use of prior knowledge on the structure of vectors in the relevant domain.
Collision-based Testers are Optimal for Uniformity and Closeness
We study the fundamental problems of (i) uniformity testing of a discrete distribution, and (ii) closeness testing between two discrete distributions with bounded $\ell_2$-norm.
Extensions and Limitations of the Neural GPU
We find that these techniques increase the set of algorithmic problems that can be solved by the Neural GPU: we have been able to learn to perform all the arithmetic operations (and generalize to arbitrarily long numbers) when the arguments are given in the decimal representation (which, surprisingly, has not been possible before).
Equality of Opportunity in Supervised Learning
We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features.
Binary Embedding: Fundamental Limits and Fast Algorithm
Binary embedding is a nonlinear dimension reduction methodology where high dimensional data are embedded into the Hamming cube while preserving the structure of the original space.
Data Structures and Algorithms Information Theory Information Theory
Tight bounds for learning a mixture of two gaussians
Denoting by $\sigma^2$ the variance of the unknown mixture, we prove that $\Theta(\sigma^{12})$ samples are necessary and sufficient to estimate each parameter up to constant additive error when $d=1.$ Our upper bound extends to arbitrary dimension $d>1$ up to a (provably necessary) logarithmic loss in $d$ using a novel---yet simple---dimensionality reduction technique.
The Noisy Power Method: A Meta Algorithm with Applications
The noisy power method can be seen as a meta-algorithm that has recently found a number of important applications in a broad range of machine learning problems including alternating minimization for matrix completion, streaming principal component analysis (PCA), and privacy-preserving spectral analysis.
