arXiv is an e-print service in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance and statistics.

Benchmarking Batch Deep Reinforcement Learning Algorithms

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

Limitations of the Empirical Fisher Approximation for Natural Gradient Descent

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

Adversarial camera stickers: A physical camera-based attack on deep learning systems

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Efficient Evaluation-Time Uncertainty Estimation by Improved Distillation

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

On Norm-Agnostic Robustness of Adversarial Training

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

MNIST-C: A Robustness Benchmark for Computer Vision

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

A Research Agenda: Dynamic Models to Defend Against Correlated Attacks

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Adversarial Examples Are a Natural Consequence of Test Error in Noise

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

When to use parametric models in reinforcement learning?

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Are Disentangled Representations Helpful for Abstract Visual Reasoning?

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Playing the lottery with rewards and multiple languages: lottery tickets in RL and NLP

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Uncertainty-guided Continual Learning with Bayesian Neural Networks

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Generating Diverse High-Fidelity Images with VQ-VAE-2

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck

- 2019 via Local Bibsonomy

Keywords: approximate, readings, generalization, optimization, information, compression, theory

- 2019 via Local Bibsonomy

Keywords: approximate, readings, generalization, optimization, information, compression, theory

Adversarial Self-Defense for Cycle-Consistent GANs

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

FreeLB: Enhanced Adversarial Training for Language Understanding

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Ease-of-Teaching and Language Structure from Emergent Communication

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Plan Arithmetic: Compositional Plan Vectors for Multi-Task Control

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

RTFM: Generalising to Novel Environment Dynamics via Reading

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Deep High-Resolution Representation Learning for Human Pose Estimation

Conference and Computer Vision and Pattern Recognition - 2019 via Local Bibsonomy

Keywords: dblp

Conference and Computer Vision and Pattern Recognition - 2019 via Local Bibsonomy

Keywords: dblp

Learning to Predict Without Looking Ahead: World Models Without Forward Prediction

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Are Sixteen Heads Really Better than One?

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Wasserstein Dependency Measure for Representation Learning

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Explanations can be manipulated and geometry is to blame

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Saccader: Improving Accuracy of Hard Attention Models for Vision

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Meta-Learning with Implicit Gradients

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, cs.AI, math.OC, stat.ML

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, cs.AI, math.OC, stat.ML

Benchmarking Model-Based Reinforcement Learning

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Online Continual Learning with Maximally Interfered Retrieval

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

Explainable AI for Trees: From Local Explanations to Global Understanding

- 2019 via Local Bibsonomy

Keywords: interpretable

- 2019 via Local Bibsonomy

Keywords: interpretable

Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Towards Stable and Efficient Training of Verifiably Robust Neural Networks

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Generalization in Deep Networks: The Role of Distance from Initialization

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Batch Normalization is a Cause of Adversarial Vulnerability

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

How Can We Be So Dense? The Benefits of Using Highly Sparse Representations

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Adversarial Examples Are Not Bugs, They Are Features

- 2019 via Local Bibsonomy

Keywords: adversarial

- 2019 via Local Bibsonomy

Keywords: adversarial

Bit-Flip Attack: Crushing Neural Network withProgressive Bit Search

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Benchmarking Deep Learning Hardware and Frameworks: Qualitative Metrics

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.DC, cs.LG, cs.PF

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.DC, cs.LG, cs.PF

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, cs.AI, cs.NE

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, cs.AI, cs.NE

Certified Adversarial Robustness via Randomized Smoothing

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

The Limitations of Adversarial Training and the Blind-Spot Attack

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Towards Interpretable Deep Neural Networks by Leveraging Adversarial Examples

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Adversarial Initialization - when your network performs the way I want

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Robustness of Generalized Learning Vector Quantization Models against Adversarial Attacks

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, cs.AI, cs.CV, stat.ML

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, cs.AI, cs.CV, stat.ML

Large-Batch Training for LSTM and Beyond

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, stat.ML

Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.CV

Hierarchical Autoregressive Image Models with Auxiliary Decoders

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.CL

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.CL

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.CV, cs.GR, cs.LG

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.CV, cs.GR, cs.LG

HellaSwag: Can a Machine Really Finish Your Sentence?

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.CL

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.CL

Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask

- 2019 via Local Bibsonomy

Keywords: pruning, nas

- 2019 via Local Bibsonomy

Keywords: pruning, nas

Meta-learners' learning dynamics are unlike learners'

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.LG, cs.AI, stat.ML

Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

S$^\mathbf{4}$L: Self-Supervised Semi-Supervised Learning

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.CV, cs.LG

more

arXiv e-Print archive - 2019 via Local arXiv

Keywords: cs.CV, cs.LG

On the Pitfalls of Measuring Emergent Communication

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

The Lottery Ticket Hypothesis at Scale

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

Generating Long Sequences with Sparse Transformers

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2019 via Local Bibsonomy

Keywords: dblp