先睹为快:神经网络顶会ICLR 2019论文热点分析

    ICLR-2019（International Conference on Learning Representations 2019），将于2019年5月9日在美国路易斯安那州的新奥尔良举行，这也是2019年最新的一个国际性的AI顶会。目前，ICLR-2019的最新接受的论文已经Release出来了，本文对本届会议接受的论文进行整理，按照统计方法，抽取出了其中集中程度最高的27个主题，并抽样了每个主题下的一些最新论文，提供给需要的朋友周末充电。

ICLR-2019接受全部论文地址

https://openreview.net/group?id=ICLR.cc/2019/Conference#accepted-oral-papers

主题热点

    Deep reinforcement learning

    Generative adversarial networks

    Deep learning

    Deep neural Network

    Domain adaptation

    Recurrent neural network

    Neural architecture search

    Convolutional networks network

    Deep networks

    Graph neural network

    Bayesian neural Network

    Variational autoencoders

    Gradient descent optimization

    Unsupervised learning

    Adversarial examples/Adversarial attacks/Adversarial training

    Imitation learning

    Generalization bounds

    Monte carlo method

    Representation learning

    Neural program

    Experience replay

    Batch normalization

    Word embeddings

    Neural machine translation

    Transfer learning

    Program synthesis

    Image-to-image translation

热点论文推荐

Reinforcement learning

    Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees

    M^3RL: Mind-aware Multi-agent Management Reinforcement Learning

    Information-Directed Exploration for Deep Reinforcement Learning

    Near-Optimal Representation Learning for Hierarchical Reinforcement Learning

    Adversarial Imitation via Variational Inverse Reinforcement Learning

    Deep reinforcement learning with relational inductive biases

    Variance Reduction for Reinforcement Learning in Input-Driven Environments

    Recall Traces: Backtracking Models for Efficient Reinforcement Learning

    Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization

    Contingency-Aware Exploration in Reinforcement Learning

    Learning to Schedule Communication in Multi-agent Reinforcement Learning

    Modeling the Long Term Future in Model-Based Reinforcement Learning

    Visceral Machines: Reinforcement Learning with Intrinsic Physiological Rewards

    From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following

    Recurrent Experience Replay in Distributed Reinforcement Learning

    Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning

    NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning

    Hierarchical Reinforcement Learning with Hindsight

Generative adversarial networks

    A generative adversarial network for style modeling in a text-to-speech system

    KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial Networks

    ROBUST ESTIMATION VIA GENERATIVE ADVERSARIAL NETWORKS

    Improving Generalization and Stability of Generative Adversarial Networks

    On Self Modulation for Generative Adversarial Networks

    Scalable Unbalanced Optimal Transport using Generative Adversarial Networks

    Visualizing and Understanding Generative Adversarial Networks

    Learning from Incomplete Data with Generative Adversarial Networks

    A Direct Approach to Robust Deep Learning Using Adversarial Networks

    A Variational Inequality Perspective on Generative Adversarial Networks

    On Computation and Generalization of Generative Adversarial Networks under Spectrum Control

    RelGAN: Relational Generative Adversarial Networks for Text Generation

    Diversity-Sensitive Conditional Generative Adversarial Networks

Scalable Reversible Generative Models with Free-form Continuous Dynamics

    Optimal Transport Maps For Distribution Preserving Operations on Latent Spaces of Generative Models

    Do Deep Generative Models Know What They Don't Know?

    Learning Localized Generative Models for 3D Point Clouds via Graph Convolution

    Distribution-Interpolation Trade off in Generative Models

    Kernel Change-point Detection with Auxiliary Deep Generative Models

Multi-Domain Adversarial Learning

    SPIGAN: Privileged Adversarial Learning from Simulation

Deep learning

    Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning

    SGD Converges to Global Minimum in Deep Learning via Star-convex Path

    Dynamic Sparse Graph for Efficient Deep Learning

    Quasi-hyperbolic momentum and Adam for deep learning

    DeepOBS: A Deep Learning Optimizer Benchmark Suite

    Deep Learning 3D Shapes Using Alt-az Anisotropic 2-Sphere Convolution

    DELTA: DEEP LEARNING TRANSFER USING FEATURE MAP WITH ATTENTION FOR CONVOLUTIONAL NETWORKS

    Deep learning generalizes because the parameter-function map is biased towards simple functions

Deep neural Network

    An Empirical Study of Example Forgetting during Deep Neural Network Learning

    Energy-Constrained Compression for Deep Neural Networks via Weighted Sparse Projection and Layer Input Masking

    Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology

    Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks

    On the loss landscape of a class of deep neural networks with no bad local valleys

    Double Viterbi: Weight Encoding for High Compression Ratio and Fast On-Chip Reconstruction for Deep Neural Network

    Minimal Images in Deep Neural Networks: Fragile Object Recognition in Natural Images

    Bias-Reduced Uncertainty Estimation for Deep Neural Classifiers

    Adaptive Estimators Show Information Compression in Deep Neural Networks

Domain adaptation

    Augmented Cyclic Adversarial Learning for Low Resource Domain Adaptation

    Unsupervised Domain Adaptation for Distance Metric Learning

    ADVERSARIAL DOMAIN ADAPTATION FOR STABLE BRAIN-MACHINE INTERFACES

    LEARNING FACTORIZED REPRESENTATIONS FOR OPEN-SET DOMAIN ADAPTATION

    Improving the Generalization of Adversarial Training with Domain Adaptation

    Regularized Learning for Domain Adaptation under Label Shifts

Recurrent neural network

    Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks

    A MAX-AFFINE SPLINE PERSPECTIVE OF RECURRENT NEURAL NETWORKS

    Quaternion Recurrent Neural Networks

    Variational Smoothing in Recurrent Neural Network Language Models

    Generalized Tensor Models for Recurrent Neural Networks

    AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks

Neural architecture search

    Efficient Multi-Objective Neural Architecture Search via Lamarckian Evolution

    ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

    Learnable Embedding Space for Efficient Neural Architecture Compression

    Graph HyperNetworks for Neural Architecture Search

    SNAS: stochastic neural architecture search

    DARTS: Differentiable Architecture Search

Convolutional networks network

    Deep Bayesian Convolutional Networks with Many Channels are Gaussian Processes

    LanczosNet: Multi-Scale Deep Graph Convolutional Networks

    Deep Convolutional Networks as shallow Gaussian Processes

    STCN: Stochastic Temporal Convolutional Networks

Convolutional Neural Networks on Non-uniform Geometrical Signals Using Euclidean Spectral Transformation

    A rotation-equivariant convolutional neural network model of primary visual cortex

    Human-level Protein Localization with Convolutional Neural Networks

Deep networks

    Critical Learning Periods in Deep Networks

    Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks

    RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks

    Predicting the Generalization Gap in Deep Networks with Margin Distributions

    Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience

Graph neural network

    How Powerful are Graph Neural Networks?

    Capsule Graph Neural Network

    Adversarial Attacks on Graph Neural Networks via Meta Learning

    Supervised Community Detection with Line Graph Neural Networks

Bayesian neural Network

    Deterministic Variational Inference for Robust Bayesian Neural Networks

    Function Space Particle Optimization for Bayesian Neural Networks

    Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network

    FUNCTIONAL VARIATIONAL BAYESIAN NEURAL NETWORKS

Variational autoencoders

    MAE: Mutual Posterior-Divergence Regularization for Variational AutoEncoders

    Learning Latent Superstructures in Variational Autoencoders for Deep Multidimensional Clustering

    Variational Autoencoders with Jointly Optimized Latent Dependency Structure

    Lagging Inference Networks and Posterior Collapse in Variational Autoencoders

Gradient descent optimization

    Gradient descent aligns the layers of deep linear networks

    Gradient Descent Provably Optimizes Over-parameterized Neural Networks

    A Convergence Analysis of Gradient Descent for Deep Linear Neural Networks

    Fluctuation-dissipation relations for stochastic gradient descent

Unsupervised learning

    Learning Unsupervised Learning Rules

    Unsupervised Learning of the Set of Local Maxima

    Unsupervised Learning via Meta-Learning

Adversarial examples/Adversarial attacks/Adversarial training

    Prior Convictions: Black-box Adversarial Attacks with Bandits and Priors

    PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks

    The Limitations of Adversarial Training and the Blind-Spot Attack

    Generalizable Adversarial Training via Spectral Normalization

    Cost-Sensitive Robustness against Adversarial Examples

    Characterizing Audio Adversarial Examples Using Temporal Dependency

    Are adversarial examples inevitable?

Imitation learning

    Sample Efficient Imitation Learning for Continuous Control

    Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning

    Generative predecessor models for sample-efficient imitation learning

Generalization bounds

    Non-vacuous Generalization Bounds at the ImageNet Scale: a PAC-Bayesian Compression Approach

    Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds

Monte carlo method

    Probabilistic Planning with Sequential Monte Carlo methods

    Bayesian Modelling and Monte Carlo Inference for GAN

    Doubly Reparameterized Gradient Estimators for Monte Carlo Objectives

Representation learning

    Measuring Compositionality in Representation Learning

    SOM-VAE: Interpretable Discrete Representation Learning on Time Series

The Laplacian in RL: Learning Representations with Efficient Approximations

    Learning Actionable Representations with Goal Conditioned Policies

    Learning Programmatically Structured Representations with Perceptor Gradients

Neural program

    Neural Program Repair by Jointly Learning to Localize and Repair

Experience replay

    DHER: Hindsight Experience Replay for Dynamic Goals

    Competitive experience replay

Batch normalization

    Towards Understanding Regularization in Batch Normalization

    A Mean Field Theory of Batch Normalization

    Theoretical Analysis of Auto Rate-Tuning by Batch Normalization

Word embeddings

    Understanding Composition of Word Embeddings via Tensor Decomposition

    Unsupervised Hyper-alignment for Multilingual Word Embeddings

    Poincare Glove: Hyperbolic Word Embeddings

Neural machine translation

    Identifying and Controlling Important Neurons in Neural Machine Translation

    Multilingual Neural Machine Translation with Knowledge Distillation

    Multilingual Neural Machine Translation With Soft Decoupled Encoding

Transfer learning

    K For The Price Of 1: Parameter Efficient Multi-task And Transfer Learning

    Transfer Learning for Sequences via Learning to Collocate

    An analytic theory of generalization dynamics and transfer learning in deep linear networks

Program synthesis

    Execution-Guided Neural Program Synthesis

    Learning a Meta-Solver for Syntax-Guided Program Synthesis

    Synthetic Datasets for Neural Program Synthesis

Image-to-image translation

    Harmonic Unpaired Image-to-image Translation

    Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency

    Instance-aware Image-to-Image Translation

往期精品内容

苏黎世联邦理工推荐信workshop | 数据科学 数据分析方法

深度学习与计算机视觉任务应用综述

Geffery Hinton-数字代表模型从数据中抽取的知识、AI不会有寒冬

统治华尔街的量化交易，入门只需看懂这几点

机器学习泰斗- Michael I.Jordan-机器学习前景与挑战

好书推荐-《深度学习基础-构建下一代机器学习算法》免费下载

10月最新-深度强化学习圣经-《Reinforcement Learning-第二版》

深度学习工业级部署实践：基于Spark部署Tensorflow深度学习模型

波士顿动力-唱歌、跳舞、后空翻-无所不能的机器人特辑

知识图谱中的深度学习技术应用概述

深度学习介绍：理论、用例与工具

<好书推荐> -《Pro Deep Learning with TensorFlow》分享

扫描下方二维码可以订阅哦！

DeepLearning_NLP

深度学习与NLP

       商务合作请联系微信号：lqfarmerlq