Search Results for author:
Found 80 papers, 30 papers with code
Evaluating Machine Accuracy on ImageNet
We perform an in-depth evaluation of human accuracy on the ImageNet dataset.
Gradient Descent Provably Solves Nonlinear Tomographic Reconstruction
We show that this approach reduces metal artifacts compared to a commercial reconstruction of a human skull with metal dental crowns.
K-Planes: Explicit Radiance Fields in Space, Time, and Appearance
We introduce k-planes, a white-box model for radiance fields in arbitrary dimensions.
Ranked #2 on
Novel View Synthesis
on NeRF
Towards Psychologically-Grounded Dynamic Preference Models
Second, we discuss implications of dynamic preference models for recommendation systems evaluation and design.
Plenoxels: Radiance Fields without Neural Networks
We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis.
Quantifying Availability and Discovery in Recommender Systems via Stochastic Reachability
In this work, we consider how preference models in interactive recommendation systems determine the availability of content and users' opportunities for discovery.
Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data
Collecting more diverse and representative training data is often touted as a remedy for the disparate performance of machine learning predictors across subpopulations.
Patterns, predictions, and actions: A story about machine learning
This graduate textbook on machine learning tells a story of how patterns in data support predictions and consequential actions.
Interpolating Classifiers Make Few Mistakes
Under the assumption that the data is independently and identically distributed, the mistake bound implies that MNIC generalizes at a rate proportional to the norm of the interpolating solution and inversely proportional to the number of data points.
Towards Robust Data-Driven Control Synthesis for Nonlinear Systems with Actuation Uncertainty
Modern nonlinear control theory seeks to endow systems with properties such as stability and safety, and has been deployed successfully across various domains.
Do Offline Metrics Predict Online Performance in Recommender Systems?
We observe that offline metrics are correlated with online performance over a range of environments.
Guaranteeing Safety of Learned Perception Modules via Measurement-Robust Control Barrier Functions
The guarantees ensured by these controllers often rely on accurate estimates of the system state for determining control actions.
A Generalizable and Accessible Approach to Machine Learning with Global Satellite Imagery
Combining satellite imagery with machine learning (SIML) has the potential to address global challenges by remotely estimating socioeconomic and environmental conditions in data-poor regions, yet the resource requirements of SIML limit its accessibility and use.
Certainty Equivalent Perception-Based Control
In order to certify performance and safety, feedback control requires precise characterization of sensor errors.
Measuring Robustness to Natural Distribution Shifts in Image Classification
We study how robust current ImageNet models are to distribution shifts arising from natural variations in datasets.
Ranked #41 on
Domain Generalization
on VizWiz-Classification
Active Learning for Nonlinear System Identification with Guarantees
While the identification of nonlinear dynamical systems is a fundamental building block of model-based reinforcement learning and feedback control, its sample complexity is only understood for systems that either have discrete states and actions or for systems that can be identified from data generated by i. i. d.
The Effect of Natural Distribution Shift on Question Answering Models
We build four new test sets for the Stanford Question Answering Dataset (SQuAD) and evaluate the ability of question-answering systems to generalize to new data.
Post-Estimation Smoothing: A Simple Baseline for Learning with Side Information
Observational data are often accompanied by natural structural indices, such as time stamps or geographic locations, which are meaningful to prediction tasks but are often discarded.
Neural Kernels Without Tangents
We investigate the connections between neural networks and simple building blocks in kernel space.
Recommendations and User Agency: The Reachability of Collaboratively-Filtered Information
When the systems are deployed, these models determine the availability of content and information to different users.
A Meta-Analysis of Overfitting in Machine Learning
By systematically comparing the public ranking with the final ranking, we assess how much participants adapted to the holdout set over the course of a competition.
When Robustness Doesn’t Promote Robustness: Synthetic vs. Natural Distribution Shifts on ImageNet
We conduct a large experimental comparison of various robustness metrics for image classification.
Robust Guarantees for Perception-Based Control
Motivated by vision-based control of autonomous vehicles, we consider the problem of controlling a known linear dynamical system for which partial state information, such as vehicle position, is extracted from complex and nonlinear data, such as a camera image.
Do Image Classifiers Generalize Across Time?
Additionally, we evaluate three detection models and show that natural perturbations induce both classification as well as localization errors, leading to a median drop in detection mAP of 14 points.
Towards augmenting crisis counselor training by improving message retrieval
A fundamental challenge when training counselors is presenting novices with the opportunity to practice counseling distressed individuals without exacerbating a situation.
Finite-time Analysis of Approximate Policy Iteration for the Linear Quadratic Regulator
We study the sample complexity of approximate policy iteration (PI) for the Linear Quadratic Regulator (LQR), building on a recent line of work using LQR as a testbed to understand the limits of reinforcement learning (RL) algorithms on continuous control tasks.
Model Similarity Mitigates Test Set Overuse
Excessive reuse of test data has become commonplace in today's machine learning workflows.
A Systematic Framework for Natural Perturbations from Videos
We introduce a systematic framework for quantifying the robustness of classifiers to naturally occurring perturbations of images found in videos.
Certainty Equivalence is Efficient for Linear Quadratic Control
We show that for both the fully and partially observed settings, the sub-optimality gap between the cost incurred by playing the certainty equivalent controller on the true system and the cost incurred by using the optimal LQ controller enjoys a fast statistical rate, scaling as the square of the parameter error.
Do ImageNet Classifiers Generalize to ImageNet?
We evaluate a broad range of models and find accuracy drops of 3% - 15% on CIFAR-10 and 11% - 14% on ImageNet.
Learning Linear Dynamical Systems with Semi-Parametric Least Squares
We analyze a simple prefiltered variation of the least squares estimator for the problem of estimation with biased, semi-parametric noise, an error model studied more broadly in causal statistics and active learning.
The Gap Between Model-Based and Model-Free Methods on the Linear Quadratic Regulator: An Asymptotic Viewpoint
The effectiveness of model-based versus model-free methods is a long-standing question in reinforcement learning (RL).
Simple random search of static linear policies is competitive for reinforcement learning
Common evaluation methodology shows that our method matches state-of-the-art sample efficiency on the benchmark MuJoCo locomotion tasks.
A System for Massively Parallel Hyperparameter Tuning
Modern learning models are characterized by large hyperparameter spaces and long training times.
Minimax Lower Bounds for $\mathcal{H}_\infty$-Norm Estimation
The problem of estimating the $\mathcal{H}_\infty$-norm of an LTI system from noisy input/output measurements has attracted recent attention as an alternative to parameter identification for bounding unmodeled dynamics in robust control.
A Successive-Elimination Approach to Adaptive Robotic Sensing
We study an adaptive source seeking problem, in which a mobile robot must identify the strongest emitter(s) of a signal in an environment with background emissions.
Safely Learning to Control the Constrained Linear Quadratic Regulator
We study the constrained linear quadratic regulator with unknown dynamics, addressing the tension between safety and exploration in data-driven control techniques.
A Tour of Reinforcement Learning: The View from Continuous Control
This manuscript surveys reinforcement learning from the perspective of optimization and control with a focus on continuous control applications.
Do CIFAR-10 Classifiers Generalize to CIFAR-10?
Although we ensure that the new test set is as close to the original data distribution as possible, we find a large drop in accuracy (4% to 10%) for a broad range of deep learning models.
Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator
We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs.
Tight Query Complexity Lower Bounds for PCA via Finite Sample Deformed Wigner Law
We show that for every $\mathtt{gap} \in (0, 1/2]$, there exists a distribution over matrices $\mathbf{M}$ for which 1) $\mathrm{gap}_r(\mathbf{M}) = \Omega(\mathtt{gap})$ (where $\mathrm{gap}_r(\mathbf{M})$ is the normalized gap between the $r$ and $r+1$-st largest-magnitude eigenvector of $\mathbf{M}$), and 2) any algorithm $\mathsf{Alg}$ which takes fewer than $\mathrm{const} \times \frac{r \log d}{\sqrt{\mathtt{gap}}}$ queries fails (with overwhelming probability) to identity a matrix $\widehat{\mathsf{V}} \in \mathbb{R}^{d \times r}$ with orthonormal columns for which $\langle \widehat{\mathsf{V}}, \mathbf{M} \widehat{\mathsf{V}}\rangle \ge (1 - \mathrm{const} \times \mathtt{gap})\sum_{i=1}^r \lambda_i(\mathbf{M})$.
Finite-Data Performance Guarantees for the Output-Feedback Control of an Unknown System
As the systems we control become more complex, first-principle modeling becomes either impossible or intractable, motivating the use of machine learning techniques for the control of systems with continuous action spaces.
Simple random search provides a competitive approach to reinforcement learning
A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions.
Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification
We prove that the ordinary least-squares (OLS) estimator attains nearly minimax optimal performance for the identification of linear dynamical systems from a single observed trajectory.
Massively Parallel Hyperparameter Tuning
Modern machine learning models are characterized by large hyperparameter search spaces and prohibitively expensive training costs.
Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator
Reinforcement learning (RL) has been successfully used to solve many continuous control tasks.
First-order Methods Almost Always Avoid Saddle Points
We establish that first-order methods avoid saddle points for almost all initializations.
On the Sample Complexity of the Linear Quadratic Regulator
This paper addresses the optimal control problem known as the Linear Quadratic Regulator in the case when the dynamics are unknown.
Flare Prediction Using Photospheric and Coronal Image Data
This is the first attempt to predict solar flares using photospheric vector magnetic field data as well as multiple wavelengths of image data from the chromosphere, transition region, and corona.
Non-Asymptotic Analysis of Robust Control from Coarse-Grained Identification
We derive bounds on the number of noisy input/output samples from a stable linear time-invariant system that are sufficient to guarantee that the corresponding finite impulse response approximation is close to the true system in the $\mathcal{H}_\infty$-norm.
The Marginal Value of Adaptive Gradient Methods in Machine Learning
Adaptive optimization methods, which perform local optimization with a metric constructed from the history of iterates, are becoming increasingly popular for training deep neural networks.
On the Gap Between Strict-Saddles and True Convexity: An Omega(log d) Lower Bound for Eigenvector Approximation
We prove a \emph{query complexity} lower bound on rank-one principal component analysis (PCA).
The Simulator: Understanding Adaptive Sampling in the Moderate-Confidence Regime
Moreover, our lower bounds zero-in on the number of times each \emph{individual} arm needs to be pulled, uncovering new phenomena which are drowned out in the aggregate sample complexity.
The Power of Adaptivity in Identifying Statistical Alternatives
This paper studies the trade-off between two different kinds of pure exploration: breadth versus depth.
Understanding deep learning requires rethinking generalization
Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance.
KeystoneML: Optimizing Pipelines for Large-Scale Advanced Analytics
Modern advanced analytics applications make use of machine learning techniques and contain multiple steps of domain-specific and general-purpose processing with high resource requirements.
Saturating Splines and Feature Selection
We extend the adaptive regression spline model by incorporating saturation, the natural requirement that a function extend as a constant outside a certain range.
Gradient Descent Learns Linear Dynamical Systems
We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system from a sequence of noisy observations generated by the system.
CYCLADES: Conflict-free Asynchronous Machine Learning
We present CYCLADES, a general framework for parallelizing stochastic optimization algorithms in a shared memory setting.
On kernel methods for covariates that are rankings
This paper studies the use of reproducing kernel Hilbert space methods for learning from permutation-valued features.
Best-of-K Bandits
This paper studies the Best-of-K Bandit game: At each time the player chooses a subset S among all N-choose-K possible options and observes reward max(X(i) : i in S) where X is a random vector drawn from a joint distribution.
Large Scale Kernel Learning using Block Coordinate Descent
We demonstrate that distributed block coordinate descent can quickly solve kernel regression and classification problems with millions of data points.
Gradient Descent Converges to Minimizers
We show that gradient descent converges to a local minimizer, almost surely with random initialization.
Train faster, generalize better: Stability of stochastic gradient descent
In the non-convex case, we give a new interpretation of common practices in neural networks, and formally show that popular techniques for training large deep models are indeed stability-promoting.
Perturbed Iterate Analysis for Asynchronous Stochastic Optimization
We demonstrate experimentally on a 16-core machine that the sparse and parallel version of SVRG is in some cases more than four orders of magnitude faster than the standard SVRG algorithm.
Parallel Correlation Clustering on Big Graphs
We present C4 and ClusterWild!, two algorithms for parallel correlation clustering that run in a polylogarithmic number of rounds and achieve nearly linear speedups, provably.
Sharp Time--Data Tradeoffs for Linear Inverse Problems
We sharply characterize the convergence rate associated with a wide variety of random measurement ensembles in terms of the number of measurements and structural complexity of the signal with respect to the chosen penalty function.
Isometric sketching of any set via the Restricted Isometry Property
In this paper we show that for the purposes of dimensionality reduction certain class of structured random matrices behave similarly to random Gaussian matrices.
A General Analysis of the Convergence of ADMM
We provide a new proof of the linear convergence of the alternating direction method of multipliers (ADMM) when one of the objective terms is strongly convex.
Optimization and Control Numerical Analysis
The Randomized Causation Coefficient
We are interested in learning causal relationships between pairs of random variables, purely from observational data.
Compressive classification and the rare eclipse problem
This paper addresses the fundamental question of when convex sets remain disjoint after random projection.
Blind Deconvolution using Convex Programming
That is, we show that if $\boldsymbol{x}$ is drawn from a random subspace of dimension $N$, and $\boldsymbol{w}$ is a vector in a subspace of dimension $K$ whose basis vectors are "spread out" in the frequency domain, then nuclear norm minimization recovers $\boldsymbol{w}\boldsymbol{x}^*$ without error.
Information Theory Information Theory
Factoring nonnegative matrices with linear programs
The constraints are chosen to ensure that the matrix C selects features; these features can then be used to find a low-rank NMF of X.
Atomic norm denoising with applications to line spectral estimation
Motivated by recent work on atomic norms in inverse problems, we propose a new approach to line spectral estimation that provides theoretical guarantees for the mean-squared-error (MSE) performance in the presence of noise and without knowledge of the model order.
Information Theory Information Theory
Beneath the valley of the noncommutative arithmetic-geometric mean inequality: conjectures, case-studies, and consequences
We detail the consequences of this inequality for stochastic gradient descent and the randomized Kaczmarz algorithm for solving linear systems.
Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
Stochastic Gradient Descent (SGD) is a popular algorithm that can achieve state-of-the-art performance on a variety of machine learning tasks.
HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
Stochastic Gradient Descent (SGD) is a popular algorithm that can achieve state-of-the-art performance on a variety of machine learning tasks.
Online Identification and Tracking of Subspaces from Highly Incomplete Information
GROUSE performs exceptionally well in practice both in tracking subspaces and as an online algorithm for matrix completion.
Weighted Sums of Random Kitchen Sinks: Replacing minimization with randomization in learning
``I am training a randomly wired neural net to play tic-tac-toe,'' Sussman replied.
Exact Matrix Completion via Convex Optimization
We show that one can perfectly recover most low-rank matrices from what appears to be an incomplete set of entries.
Information Theory Information Theory
