research
∙
07/27/2023
Universal and Transferable Adversarial Attacks on Aligned Language Models
Because "out-of-the-box" large language models are capable of generating...
share
research
∙
07/18/2023
Can Neural Network Memorization Be Localized?
Recent efforts at explaining the interplay of memorization and generaliz...
research
∙
07/11/2023
Monotone deep Boltzmann machines
Deep Boltzmann machines (DBMs), one of the first “deep” learning methods...
research
∙
07/10/2023
Leveraging Multiple Descriptive Features for Robust Few-shot Image Learning
Modern image classification is based upon directly predicting model clas...
research
∙
07/06/2023
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
Large web-sourced multimodal datasets have powered a slew of new methods...
research
∙
06/26/2023
Localized Text-to-Image Generation for Free via Cross Attention Control
Despite the tremendous success in text-to-image generative models, local...
research
∙
06/25/2023
Language models are weak learners
A central notion in practical and theoretical machine learning is that o...
research
∙
06/20/2023
A Simple and Effective Pruning Approach for Large Language Models
As their size increases, Large Languages Models (LLMs) are natural candi...
research
∙
06/08/2023
On the Importance of Exploration for Generalization in Reinforcement Learning
Existing approaches for improving generalization in deep reinforcement l...
research
∙
06/07/2023
On the Joint Interaction of Models, Data, and Features
Learning features from data is one of the defining characteristics of de...
research
∙
05/22/2023
Neural Functional Transformers
The recent success of neural networks as implicit representation of data...
research
∙
05/16/2023
Mimetic Initialization of Self-Attention Layers
It is notoriously difficult to train Transformers on small datasets; typ...
research
∙
04/25/2023
The Update Equivalence Framework for Decision-Time Planning
The process of revising (or constructing) a policy immediately prior to ...
research
∙
03/25/2023
Learning with Explanation Constraints
While supervised learning assumes the presence of labeled data, we may h...
research
∙
03/14/2023
Sinkhorn-Flow: Predicting Probability Mass Flow in Dynamical Systems Using Optimal Transport
Predicting how distributions over discrete variables vary over time is a...
research
∙
03/13/2023
Model-tuning Via Prompts Makes NLP Models Adversarially Robust
In recent years, NLP practitioners have converged on the following pract...
research
∙
02/27/2023
Permutation Equivariant Neural Functionals
This work studies the design of neural networks that can process the wei...
research
∙
01/22/2023
Abstracting Imperfect Information Away from Two-Player Zero-Sum Games
In their seminal work, Nayyar et al. (2013) showed that imperfect inform...
research
∙
12/29/2022
Function Approximation for Solving Stackelberg Equilibrium in Large Perfect Information Games
Function approximation (FA) has been a critical component in solving lar...
research
∙
12/13/2022
Losses over Labels: Weakly Supervised Learning via Direct Loss Construction
Owing to the prohibitive costs of generating large amounts of labeled da...
research
∙
10/26/2022
Characterizing Datapoints via Second-Split Forgetting
Researchers investigating example hardness have increasingly focused on ...
research
∙
10/24/2022
Perfectly Secure Steganography Using Minimum Entropy Coupling
Steganography is the practice of encoding secret information into innocu...
research
∙
10/07/2022
Understanding the Covariance Structure of Convolutional Filters
Neural network weights are typically initialized at random from univaria...
research
∙
08/11/2022
General Cutting Planes for Bound-Propagation-Based Neural Network Verification
Bound propagation methods, when combined with branch and bound, are amon...
research
∙
06/12/2022
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
Algorithms designed for single-agent reinforcement learning (RL) general...
research
∙
05/12/2022
Smooth-Reduce: Leveraging Patches for Improved Certified Robustness
Randomized smoothing (RS) has been shown to be a fast, scalable techniqu...
research
∙
04/18/2022
Deep Equilibrium Optical Flow Estimation
Many recent state-of-the-art (SOTA) optical flow models use finite-step ...
research
∙
03/02/2022
Dojo: A Differentiable Simulator for Robotics
We present a differentiable rigid-body-dynamics simulator for robotics t...
research
∙
01/24/2022
Patches Are All You Need?
Although convolutional networks have been the dominant architecture for ...
research
∙
11/25/2021
Joint inference and input optimization in equilibrium networks
Many tasks in deep learning involve optimizing over the inputs to a netw...
research
∙
11/12/2021
Adversarially Robust Learning for Security-Constrained Optimal Power Flow
In recent years, the ML community has seen surges of interest in both ad...
research
∙
11/02/2021
Training Certifiably Robust Neural Networks with Efficient Local Lipschitz Bounds
Certified robustness is a desirable property for deep neural networks in...
research
∙
06/28/2021
Stabilizing Equilibrium Models by Jacobian Regularization
Deep equilibrium networks (DEQs) are a new class of models that eschews ...
research
∙
06/25/2021
Assessing Generalization of SGD via Disagreement
We empirically show that the test error of deep networks can be estimate...
research
∙
06/16/2021
DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting
Analyzing the worst-case performance of deep neural networks against inp...
research
∙
06/11/2021
DORO: Distributional and Outlier Robust Optimization
Many machine learning tasks involve subpopulation shift where the testin...
research
∙
05/19/2021
Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization
While reinforcement learning (RL) is gaining popularity in energy system...
research
∙
05/01/2021
RATT: Leveraging Unlabeled Data to Guarantee Generalization
To assess generalization, machine learning scientists typically either (...
research
∙
04/25/2021
DC3: A learning method for optimization with hard constraints
Large optimization problems with hard constraints arise in many settings...
research
∙
04/14/2021
Orthogonalizing Convolutional Layers with the Cayley Transform
Recent work has highlighted several advantages of enforcing orthogonalit...
research
∙
03/11/2021
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Verification
Recent works in neural network verification show that cheap incomplete v...
research
∙
02/26/2021
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
We empirically demonstrate that full-batch gradient descent on neural ne...
research
∙
02/20/2021
On Proximal Policy Optimization's Heavy-tailed Gradients
Modern policy gradient algorithms, notably Proximal Policy Optimization ...
research
∙
01/28/2021
A Bayesian Model of Cash Bail Decisions
The use of cash bail as a mechanism for detaining defendants pre-trial i...
research
∙
12/05/2020
Deep Archimedean Copulas
A central problem in machine learning and statistics is to model joint d...
research
∙
12/04/2020
Challenging common interpretability assumptions in feature attribution explanations
As machine learning and algorithmic decision making systems are increasi...
research
∙
12/04/2020
Community detection using fast low-cardinality semidefinite programming
Modularity maximization has been a fundamental tool for understanding th...
research
∙
12/04/2020
Efficient semidefinite-programming-based inference for binary and multi-class MRFs
Probabilistic inference in pairwise Markov Random Fields (MRFs), i.e. co...
research
∙
11/16/2020
Enforcing robust control guarantees within neural network policies
When designing controllers for safety-critical systems, practitioners of...
research
∙
10/18/2020