
RATT: Leveraging Unlabeled Data to Guarantee Generalization
To assess generalization, machine learning scientists typically either (...
read it

DC3: A learning method for optimization with hard constraints
Large optimization problems with hard constraints arise in many settings...
read it

Orthogonalizing Convolutional Layers with the Cayley Transform
Recent work has highlighted several advantages of enforcing orthogonalit...
read it

BetaCROWN: Efficient Bound Propagation with Perneuron Split Constraints for Complete and Incomplete Neural Network Verification
Recent works in neural network verification show that cheap incomplete v...
read it

Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
We empirically demonstrate that fullbatch gradient descent on neural ne...
read it

On Proximal Policy Optimization's Heavytailed Gradients
Modern policy gradient algorithms, notably Proximal Policy Optimization ...
read it

A Bayesian Model of Cash Bail Decisions
The use of cash bail as a mechanism for detaining defendants pretrial i...
read it

Deep Archimedean Copulas
A central problem in machine learning and statistics is to model joint d...
read it

Challenging common interpretability assumptions in feature attribution explanations
As machine learning and algorithmic decision making systems are increasi...
read it

Community detection using fast lowcardinality semidefinite programming
Modularity maximization has been a fundamental tool for understanding th...
read it

Efficient semidefiniteprogrammingbased inference for binary and multiclass MRFs
Probabilistic inference in pairwise Markov Random Fields (MRFs), i.e. co...
read it

Enforcing robust control guarantees within neural network policies
When designing controllers for safetycritical systems, practitioners of...
read it

Poisoned classifiers are not only backdoored, they are fundamentally broken
Under a commonlystudied "backdoor" poisoning attack against classificat...
read it

Gaussian MRF Covariance Modeling for Efficient BlackBox Adversarial Attacks
We study the problem of generating adversarial examples in a blackbox s...
read it

Learning perturbation sets for robust machine learning
Although much progress has been made towards robust deep learning, a sig...
read it

Hard Label Blackbox Adversarial Attacks in Low Query Budget Regimes
We focus on the problem of blackbox adversarial attacks, where the aim ...
read it

Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
Solving large complex partial differential equations (PDEs), such as tho...
read it

Provably Safe PACMDP Exploration Using Analogies
A key challenge in applying reinforcement learning to safetycritical do...
read it

Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications
Recent work has shown that it is possible to learn neural networks with ...
read it

Multiscale Deep Equilibrium Models
We propose a new class of implicit networks, the multiscale deep equilib...
read it

Monotone operator equilibrium networks
Implicitdepth models such as Deep Equilibrium Networks have recently be...
read it

Blackbox Smoothing: A Provable Defense for Pretrained Classifiers
We present a method for provably defending any pretrained image classifi...
read it

Overfitting in adversarially robust deep learning
It is common practice in deep learning to use overparameterized networks...
read it

Certified Robustness to LabelFlipping Attacks via Randomized Smoothing
Machine learning algorithms are known to be susceptible to data poisonin...
read it

Learning Stable Deep Dynamics Models
Deep networks are commonly used to model dynamical systems, predicting h...
read it

Fast is better than free: Revisiting adversarial training
Adversarial training, a method for learning robust deep networks, is typ...
read it

APPerf: Incorporating Generic Performance Metrics in Differentiable Learning
We propose a method that enables practitioners to conveniently incorpora...
read it

Dynamic Modeling and Equilibria in Fair Decision Making
Recent studies on fairness in automated decision making systems have bot...
read it

Adversarial Music: Real World Audio Adversary Against Wakeword Detection System
Voice Assistants (VAs) such as Amazon Alexa or Google Assistant rely on ...
read it

Blackbox Adversarial Attacks with Bayesian Optimization
We focus on the problem of blackbox adversarial attacks, where the aim ...
read it

Adversarial Robustness Against the Union of Multiple Perturbation Models
Owing to the susceptibility of deep learning systems to adversarial atta...
read it

Deep Equilibrium Models
We present a new approach to modeling sequential data: the deep equilibr...
read it

The Limited MultiLabel Projection Layer
We propose the Limited MultiLabel (LML) projection layer as a new primi...
read it

Perceptual Based Adversarial Audio Attacks
Recent work has shown the possibility of adversarial attacks on automati...
read it

Multimodal Transformer for Unaligned Multimodal Language Sequences
Human language is often multimodal, which comprehends a mixture of natur...
read it

Deterministic PACBayesian generalization bounds for deep networks via generalizing noiseresilience
The ability of overparameterized deep networks to generalize well has be...
read it

Adversarial camera stickers: A physical camerabased attack on deep learning systems
Recent work has thoroughly documented the susceptibility of deep learnin...
read it

Adversarial camera stickers: A Physical Camera Attack on Deep Learning Classifier
Recent work has thoroughly documented the susceptibility of deep learnin...
read it

Large Scale Learning of Agent Rationality in TwoPlayer ZeroSum Games
With the recent advances in solving large, zerosum extensive form games...
read it

Wasserstein Adversarial Examples via Projected Sinkhorn Iterations
A rapidly growing area of work has studied the existence of adversarial ...
read it

Uniform convergence may be unable to explain generalization in deep learning
We cast doubt on the power of uniform convergencebased generalization b...
read it

Certified Adversarial Robustness via Randomized Smoothing
Recent work has shown that any classifier which classifies well under Ga...
read it

Generalization in Deep Networks: The Role of Distance from Initialization
Why does training deep neural networks using stochastic gradient descent...
read it

Lowrank semidefinite programming for the MAX2SAT problem
This paper proposes a new algorithm for solving MAX2SAT problems based o...
read it

Differentiable MPC for Endtoend Planning and Control
We present foundations for using Model Predictive Control (MPC) as a dif...
read it

A ContinuousTime View of Early Stopping for Least Squares Regression
We study the statistical properties of the iterates generated by gradien...
read it

Trellis Networks for Sequence Modeling
We present trellis networks, a new architecture for sequence modeling. O...
read it

Scaling provable adversarial defenses
Recent work has developed methods for learning deep network classifiers ...
read it

What game are we playing? Endtoend learning in normal and extensive form games
Although recent work in AI has made great progress in solving large, zer...
read it

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
For most deep learning practitioners, sequence modeling is synonymous wi...
read it
J. Zico Kolter
is this you? claim profile