Search Results for author:
Found 49 papers, 13 papers with code
Near-minimax recursive density estimation on the binary hypercube
This paper describes a recursive estimation procedure for multivariate binary densities using orthogonal expansions.
Relax but stay in control: from value to algorithms for online Markov decision processes
Online learning algorithms are designed to perform in non-stationary environments, but generally there is no notion of a dynamic state to model constraints on current and future actions as a function of past actions.
Online Markov decision processes with Kullback-Leibler control cost
This paper considers an online (real-time) control problem that involves an agent performing a discrete-time random walk over a finite state space.
Matrix Completion Under Monotonic Single Index Models
Most recent results in matrix completion assume that the matrix under consideration is low-rank or that the columns are in a union of low-rank subspaces.
On Learning High Dimensional Structured Single Index Models
Single Index Models (SIMs) are simple yet flexible semi-parametric models for machine learning, where the response variable is modeled as a monotonic function of a linear combination of features.
Inference of High-dimensional Autoregressive Generalized Linear Models
For instance, each element of an observation vector could correspond to a different node in a network, and the parameters of an autoregressive model would correspond to the impact of the network structure on the time series evolution.
Online Data Thinning via Multi-Subspace Tracking
At the heart of this proposed approach is an online anomaly detection method based on dynamic, low-rank Gaussian mixture models.
Improved Strongly Adaptive Online Learning using Coin Betting
This paper describes a new parameter-free online learning algorithm for changing environments.
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.
Scalable Generalized Linear Bandits: Online Computation and Hashing
Second, for the case where the number $N$ of arms is very large, we propose new algorithms in which each next arm is selected via an inner product search.
Subspace Clustering with Missing and Corrupted Data
Given full or partial information about a collection of points that lie close to a union of several subspaces, subspace clustering refers to the process of clustering the points according to their subspace and identifying the subspaces.
Online Learning for Changing Environments using Coin Betting
A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments.
Subspace Clustering via Tangent Cones
Given samples lying on any of a number of subspaces, subspace clustering is the task of grouping the samples based on the their corresponding subspaces.
Network Estimation from Point Process Data
Using our general framework, we provide a number of novel theoretical guarantees for high-dimensional self-exciting point processes that reflect the role played by the underlying network structure and long-term memory.
Missing Data in Sparse Transition Matrix Estimation for Sub-Gaussian Vector Autoregressive Processes
In such a scenario, where covariates are highly interdependent and partially missing, new theoretical challenges arise.
Graph-based regularization for regression problems with alignment and highly-correlated designs
This work considers a high-dimensional regression setting in which a graph governs both correlations among the covariates and the similarity among regression coefficients -- meaning there is \emph{alignment} between the covariates and regression coefficients.
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.
Estimating Network Structure from Incomplete Event Data
Multivariate Bernoulli autoregressive (BAR) processes model time series of events in which the likelihood of current events is determined by the times and locations of past events.
Bilinear Bandits with Low-rank Structure
We introduce the bilinear bandit problem with low-rank structure in which an action takes the form of a pair of arms from two different entity types, and the reward is a bilinear function of the known feature vectors of the arms.
Neumann Networks for Inverse Problems in Imaging
We present an end-to-end, data-driven method of solving inverse problems inspired by the Neumann series, which we call a Neumann network.
Learning to Solve Linear Inverse Problems in Imaging with Neumann Networks
Recent advances have illustrated that it is often possible to learn to solve linear inverse problems in imaging using training data that can outperform more traditional regularized least squares solutions.
A Function Space View of Bounded Norm Infinite Width ReLU Nets: The Multivariate Case
In this paper, we characterize the norm required to realize a function $f:\mathbb{R}^d\rightarrow\mathbb{R}$ as a single hidden-layer ReLU network with an unbounded number of units (infinite width), but where the Euclidean norm of the weights is bounded, including precisely characterizing which functions can be realized with finite norm.
An Optimal Statistical and Computational Framework for Generalized Tensor Estimation
Under mild conditions on the loss function, we establish both an upper bound on statistical error and the linear rate of computational convergence through a general deterministic analysis.
Context-dependent self-exciting point processes: models, methods, and risk bounds in high dimensions
High-dimensional autoregressive point processes model how current events trigger or inhibit future events, such as activity by one member of a social network can affect the future activity of his or her neighbors.
Detection and Description of Change in Visual Streams
This paper presents a framework for the analysis of changes in visual streams: ordered sequences of images, possibly separated by significant time gaps.
Deep Learning Techniques for Inverse Problems in Imaging
Recent work in machine learning shows that deep neural networks can be used to solve a wide variety of inverse problems arising in computational imaging.
Model Adaptation for Inverse Problems in Imaging
Deep neural networks have been applied successfully to a wide variety of inverse problems arising in computational imaging.
Functional Linear Regression with Mixed Predictors
We derive finite sample theoretical guarantees and show that the excess prediction risk of our estimator is minimax optimal.
Statistics Theory Methodology Statistics Theory
Deep Equilibrium Architectures for Inverse Problems in Imaging
Recent efforts on solving inverse problems in imaging via deep neural networks use architectures inspired by a fixed number of iterations of an optimization method.
Data-driven Cloud Clustering via a Rotationally Invariant Autoencoder
Advanced satellite-born remote sensing instruments produce high-resolution multi-spectral data for much of the globe at a daily cadence.
Prediction in the presence of response-dependent missing labels
In a variety of settings, limitations of sensing technologies or other sampling mechanisms result in missing labels, where the likelihood of a missing label in the training set is an unknown function of the data.
Pure Exploration in Kernel and Neural Bandits
To overcome the curse of dimensionality, we propose to adaptively embed the feature representation of each arm into a lower-dimensional space and carefully deal with the induced model misspecification.
Auto-differentiable Ensemble Kalman Filters
Data assimilation is concerned with sequentially estimating a temporally-evolving state.
Adaptive Differentially Private Empirical Risk Minimization
We propose an adaptive (stochastic) gradient perturbation method for differentially private empirical risk minimization.
The Role of Linear Layers in Nonlinear Interpolating Networks
This paper explores the implicit bias of overparameterized neural networks of depth greater than two layers.
NURD: Negative-Unlabeled Learning for Online Datacenter Straggler Prediction
To predict stragglers accurately and early without labeled positive examples or assumptions on latency distributions, this paper presents NURD, a novel Negative-Unlabeled learning approach with Reweighting and Distribution-compensation that only trains on negative and unlabeled streaming data.
Cloud Classification with Unsupervised Deep Learning
We present a framework for cloud characterization that leverages modern unsupervised deep learning technologies.
Embed and Emulate: Learning to estimate parameters of dynamical systems with uncertainty quantification
This paper explores learning emulators for parameter estimation with uncertainty estimation of high-dimensional dynamical systems.
Beyond Ensemble Averages: Leveraging Climate Model Ensembles for Subseasonal Forecasting
This study explores an application of machine learning (ML) models as post-processing tools for subseasonal forecasting.
Reduced-Order Autodifferentiable Ensemble Kalman Filters
This paper introduces a computational framework to reconstruct and forecast a partially observed state that evolves according to an unknown or expensive-to-simulate dynamical system.
Bagging Provides Assumption-free Stability
Bagging is an important technique for stabilizing machine learning models.
Linear Neural Network Layers Promote Learning Single- and Multiple-Index Models
This paper explores the implicit bias of overparameterized neural networks of depth greater than two layers.
Deep Stochastic Mechanics
This paper introduces a novel deep-learning-based approach for numerical simulation of a time-evolving Schr\"odinger equation inspired by stochastic mechanics and generative diffusion models.
Training neural operators to preserve invariant measures of chaotic attractors
In this paper, we propose an alternative framework designed to preserve invariant measures of chaotic attractors that characterize the time-invariant statistical properties of the dynamics.
Integrating Uncertainty Awareness into Conformalized Quantile Regression
The reason is that the prediction intervals of CQR do not distinguish between two forms of uncertainty: first, the variability of the conditional distribution of $Y$ given $X$ (i. e., aleatoric uncertainty), and second, our uncertainty in estimating this conditional distribution (i. e., epistemic uncertainty).
Rotation-Invariant Random Features Provide a Strong Baseline for Machine Learning on 3D Point Clouds
Specifically, we extend the random features method of Rahimi & Recht 2007 by deriving a version that is invariant to three-dimensional rotations and showing that it is fast to evaluate on point cloud data.
Depth Separation in Norm-Bounded Infinite-Width Neural Networks
We also show that a similar statement in the reverse direction is not possible: any function learnable with polynomial sample complexity by a norm-controlled depth-2 ReLU network with infinite width is also learnable with polynomial sample complexity by a norm-controlled depth-3 ReLU network.
Residual Connections Harm Self-Supervised Abstract Feature Learning
We demonstrate that adding a weighting factor to decay the strength of identity shortcuts within residual networks substantially improves semantic feature learning in the state-of-the-art self-supervised masked autoencoding (MAE) paradigm.
