Search Results for author:
Found 22 papers, 2 papers with code
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
To mitigate the annotation cost of SFT and circumvent the computational bottlenecks of active learning, we propose using experimental design.
Weighted variation spaces and approximation by shallow ReLU networks
A new and more proper definition of model classes on domains is given by introducing the concept of weighted variation spaces.
Variation Spaces for Multi-Output Neural Networks: Insights on Multi-Task Learning and Network Compression
This representer theorem establishes that shallow vector-valued neural networks are the solutions to data-fitting problems over these infinite-dimensional spaces, where the network widths are bounded by the square of the number of training data.
Filtered Iterative Denoising for Linear Inverse Problems
These are often referred to as ``plug-and-play" (PnP) methods because, in principle, an off-the-shelf denoiser can be used for a variety of different inverse problems.
Deep Learning Meets Sparse Regularization: A Signal Processing Perspective
Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks.
PathProx: A Proximal Gradient Algorithm for Weight Decay Regularized Deep Neural Networks
Weight decay is one of the most widely used forms of regularization in deep learning, and has been shown to improve generalization and robustness.
Near-Minimax Optimal Estimation With Shallow ReLU Neural Networks
We study the problem of estimating an unknown function from noisy data using shallow ReLU neural networks.
What Kinds of Functions do Deep Neural Networks Learn? Insights from Variational Spline Theory
The function space consists of compositions of functions from the Banach spaces of second-order bounded variation in the Radon domain.
Banach Space Representer Theorems for Neural Networks and Ridge Splines
We derive a representer theorem showing that finite-width, single-hidden layer neural networks are solutions to these inverse problems.
Optimal Confidence Regions for the Multinomial Parameter
More precisely, consider an empirical distribution $\widehat{\boldsymbol{p}}$ generated from $n$ iid realizations of a random variable that takes one of $k$ possible values according to an unknown distribution $\boldsymbol{p}$.
The Role of Neural Network Activation Functions
A wide variety of activation functions have been proposed for neural networks.
MaxiMin Active Learning in Overparameterized Model Classes}
Generating labeled training datasets has become a major bottleneck in Machine Learning (ML) pipelines.
Tensor Methods for Nonlinear Matrix Completion
This approach will succeed in many cases where traditional LRMC is guaranteed to fail because the data are low-rank in the tensorized representation but not in the original representation.
Algebraic Variety Models for High-Rank Matrix Completion
We consider a generalization of low-rank matrix completion to the case where the data belongs to an algebraic variety, i. e. each data point is a solution to a system of polynomial equations.
A Characterization of Deterministic Sampling Patterns for Low-Rank Matrix Completion
Finite completability is the tipping point in LRMC, as a few additional samples of a finitely completable matrix guarantee its unique completability.
Deterministic Conditions for Subspace Identifiability from Incomplete Sampling
Consider a generic $r$-dimensional subspace of $\mathbb{R}^d$, $r<d$, and suppose that we are only given projections of this subspace onto small subsets of the canonical coordinates.
Sparse Estimation with Strongly Correlated Variables using Ordered Weighted L1 Regularization
This paper studies ordered weighted L1 (OWL) norm regularization for sparse estimation problems with strongly correlated variables.
Active Learning for Undirected Graphical Model Selection
This paper studies graphical model selection, i. e., the problem of estimating a graph of statistical relationships among a collection of random variables.
Near-Optimal Adaptive Compressed Sensing
The algorithm, termed Compressive Adaptive Sense and Search (CASS), is shown to be near-optimal in that it succeeds at the lowest possible signal-to-noise-ratio (SNR) levels, improving on previous work in adaptive compressed sensing.
The Sample Complexity of Search over Multiple Populations
We consider a large number of populations, each corresponding to either distribution P0 or P1.
Active Ranking using Pairwise Comparisons
We show that under this assumption the number of possible rankings grows like $n^{2d}$ and demonstrate an algorithm that can identify a randomly selected ranking using just slightly more than $d log n$ adaptively selected pairwise comparisons, on average.
The Geometry of Generalized Binary Search
GBS is a well-known greedy algorithm for determining a binary-valued function through a sequence of strategically selected queries.
