Deep Learning

Do Neural Networks Really Need to Be So Big?

The Computational Limits of Deep Learning

Tiny Transfer Learning: Towards Memory-Efficient On-Device Learning

AdaShare: Learning What To Share For Efficient Deep Multi-Task Learning

Approximate Cross-Validation for Structured Models

MCUNet: Tiny Deep Learning on IoT Devices

Bio-Inspired Hashing for Unsupervised Similarity Search

Why Gradient Clipping accelerates training for neural networks

Learning Rate Rewinding for elegant neural network pruning

Generative Ratio Matching Networks

Implementation Matters in Deep RL: A Case Study on PPO and TRPO

Once for All: Train One Network and Specialize it for Efficient Deployment

Deep Audio Priors Emerge From Harmonic Convolutional Networks

A Closer Look at Deep Policy Gradients

Deep Symbolic Superoptimization Without Human Knowledge

ObjectNet: A bias-controlled dataset object recognition

On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization

Embedding Compression with Isotropic Iterative Quantization

Point-Voxel CNN for Efficient 3D Deep Learning

Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference

Imitation learning from observations

Cross-channel Communication Networks

Deep Leakage from Gradients

Variational Russian Roulette for Deep Bayesian Nonparametrics

Unsupervised learning by competing hidden units

Tight Certificates of Adversarial Robustness

Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach

Neural Network Robustness Certification with General Activation Functions

CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networks

Co-regularized Alignment for Unsupervised Domain Adaptation

MiME: Multilevel Medical Embedding of Electronic Health Records for Predictive Healthcare

Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

BlockDrop: Dynamic Inference Paths in Residual Networks

Action Centered Contextual Bandits

Gradient Descent for Spiking Neural Networks