
The Computational Limits of Deep Learning
Deep learning's recent history has been one of achievement: from triumph...
read it

Understanding Human Judgments of Causality
Discriminating between causality and correlation is a major problem in m...
read it

The Synthesizability of Molecules Proposed by Generative Models
The discovery of functional molecules is an expensive and timeconsuming...
read it

Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization
While deep learning is successful in a number of applications, it is not...
read it

Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications
Visual events are usually accompanied by sounds in our daily lives. Howe...
read it

Interpretable Neuroevolutionary Models for Learning NonDifferentiable Functions and Programs
A key factor in the modern success of deep learning is the astonishing e...
read it

Generalized Maximum Causal Entropy for Inverse Reinforcement Learning
We consider the problem of learning from demonstrated trajectories with ...
read it

A Probe into Understanding GAN and VAE models
Both generative adversarial network models and variational autoencoders ...
read it

Data augmentation using learned transforms for oneshot medical image segmentation
Biomedical image segmentation is an important task in many medical appli...
read it

A Theory of Uncertainty Variables for State Estimation and Inference
Probability theory forms an overarching framework for modeling uncertain...
read it

Survey of Attacks and Defenses on EdgeDeployed Neural Networks
Deep Neural Network (DNN) workloads are quickly moving from datacenters ...
read it

Avoidance Learning Using Observational Reinforcement Learning
Imitation learning seeks to learn an expert policy from sampled demonstr...
read it

DiffTaichi: Differentiable Programming for Physical Simulation
We study the problem of learning and optimizing through physical simulat...
read it

Kimera: an OpenSource Library for RealTime MetricSemantic Localization and Mapping
We provide an opensource C++ library for realtime metricsemantic visu...
read it

Compositional Explanations of Neurons
We describe a procedure for explaining neurons in deep representations b...
read it

Continual Learning with SelfOrganizing Maps
Despite remarkable successes achieved by modern neural networks in a wid...
read it

Inverse Reinforcement Learning with Missing Data
We consider the problem of recovering an expert's reward function with i...
read it

Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
Domain generalization is the problem of machine learning when the traini...
read it

Uncertainty Quantification Using Neural Networks for Molecular Property Prediction
Uncertainty quantification (UQ) is an important component of molecular p...
read it

3D Traffic Simulation for Autonomous Vehicles in Unity and Python
Over the recent years, there has been an explosion of studies on autonom...
read it

On Fast Leverage Score Sampling and Optimal Learning
Leverage score sampling provides an appealing way to perform approximate...
read it

Bidirectional Inference Networks: A Class of Deep Bayesian Networks for Health Profiling
We consider the problem of inferring the values of an arbitrary set of v...
read it

Are Transformers universal approximators of sequencetosequence functions?
Despite the widespread adoption of Transformer models for NLP tasks, the...
read it

Federated Visual Classification with RealWorld Data Distribution
Federated Learning enables visual models to be trained ondevice, bringi...
read it

Adversarial Genetic Programming for Cyber Security: A Rising Application Domain Where GP Matters
Cyber security adversaries and engagements are ubiquitous and ceaseless....
read it

HAT: HardwareAware Transformers for Efficient Natural Language Processing
Transformers are ubiquitous in Natural Language Processing (NLP) tasks, ...
read it

Towards Practical MultiObject Manipulation using Relational Reinforcement Learning
Learning robotic manipulation tasks using reinforcement learning with sp...
read it

How do Data Science Workers Collaborate? Roles, Workflows, and Tools
Today, the prominence of data science within organizations has given ris...
read it

The Limitations of Adversarial Training and the BlindSpot Attack
The adversarial training procedure proposed by Madry et al. (2018) is on...
read it

Speech2Face: Learning the Face Behind a Voice
How much can we infer about a person's looks from the way they speak? In...
read it

Learning with AMIGo: Adversarially Motivated Intrinsic Goals
A key challenge for reinforcement learning (RL) consists of learning in ...
read it

Verifiably Safe Exploration for EndtoEnd Reinforcement Learning
Deploying deep reinforcement learning in safetycritical settings requir...
read it

Observational Overfitting in Reinforcement Learning
A major component of overfitting in modelfree reinforcement learning (R...
read it

Semantic Photo Manipulation with a Generative Image Prior
Despite the recent success of GANs in synthesizing images conditioned on...
read it

Theory of Minds: Understanding Behavior in Groups Through Inverse Planning
Human social behavior is structured by relationships. We form teams, gro...
read it

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
Graph representation learning resurges as a trending research subject ow...
read it

A Polynomialtime Solution for Robust Registration with Extreme Outlier Rates
We propose a robust approach for the registration of two sets of 3D poin...
read it

Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization
We recover a video of the motion taking place in a hidden scene by obser...
read it

Overinterpretation reveals image classification model pathologies
Image classifiers are typically scored on their test set accuracy, but h...
read it

Subgraph Neural Networks
Deep learning methods for graphs achieve remarkable performance on many ...
read it

Graduated NonConvexity for Robust Spatial Perception: From NonMinimal Solvers to Global Outlier Rejection
Semidefinite Programming (SDP) and SumsofSquares (SOS) relaxations hav...
read it

Minimax Semiparametric Learning With Approximate Sparsity
Many objects of interest can be expressed as a linear, mean square conti...
read it

What is the State of Neural Network Pruning?
Neural network pruning—the task of reducing the size of a network by rem...
read it

Efficiently testing local optimality and escaping saddles for ReLU networks
We provide a theoretical algorithm for checking local optimality and esc...
read it

Predicting Factuality of Reporting and Bias of News Media Sources
We present a study on predicting the factuality of reporting and bias of...
read it

CTToMR Conditional Generative Adversarial Networks for Ischemic Stroke Lesion Segmentation
Infarcted brain tissue resulting from acute stroke readily shows up as h...
read it

A Study of Compositional Generalization in Neural Models
Compositional and relational learning is a hallmark of human intelligenc...
read it

Paretooptimal data compression for binary classification tasks
The goal of lossy data compression is to reduce the storage cost of a da...
read it

Deep Context Map: Agent Trajectory Prediction using Locationspecific Latent Maps
In this paper, we propose a novel approach for agent motion prediction i...
read it

ARDA: Automatic Relational Data Augmentation for Machine Learning
Automatic machine learning () is a family of techniques to automate the ...
read it
MIT
The Massachusetts Institute of Technology is a private research university in Cambridge, Massachusetts.