6.9k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Meta (United Kingdom)GB158 papers
- Meta (Israel)IL62 papers
- Menlo SchoolUS51 papers
- New York UniversityUS49 papers
- Carnegie Mellon UniversityUS33 papers
- University of California, BerkeleyUS31 papers
- The University of Texas at AustinUS28 papers
- Google (United States)US27 papers
- Georgia Institute of TechnologyUS26 papers
- Stanford UniversityUS26 papers
- Cornell UniversityUS24 papers
- University of WashingtonUS20 papers
26 papers · 2 filters
On the Curved Geometry of Accelerated Optimization
Aaron Defazio
In this work we propose a differential geometric motivation for Nesterov's accelerated gradient method (AGM) for strongly-convex problems. By considering the optimization procedure…
GDPP: Learning Diverse Generations Using Determinantal Point Process
Mohamed Elfeki, Camille Couprie, Morgane Riviere +1
Generative models have proven to be an outstanding tool for representing high-dimensional probability distributions and generating realistic-looking images. An essential characteri…
Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning
Sainbayar Sukhbaatar, Emily Denton, Arthur Szlam +1
In hierarchical reinforcement learning a major challenge is determining appropriate low-level policies. We propose an unsupervised learning scheme, based on asymmetric self-play fr…
High-Level Strategy Selection under Partial Observability in StarCraft: Brood War
Jonas Gehring, Da Ju, Vegard Mella +3
We consider the problem of high-level strategy selection in the adversarial setting of real-time strategy games from a reinforcement learning perspective, where taking an action co…
Natural Environment Benchmarks for Reinforcement Learning
Amy Zhang, Yuxin Wu, Joelle Pineau
While current benchmark reinforcement learning (RL) tasks have been useful to drive progress in the field, they are in many ways poor substitutes for learning with real-world data.…
Private Model Compression via Knowledge Distillation
Ji Wang, Weidong Bao, Lichao Sun +3
The soaring demand for intelligent mobile applications calls for deploying powerful deep neural networks (DNNs) on mobile devices. However, the outstanding performance of DNNs noto…
Differentiable Greedy Networks
Thomas Powers, Rasool Fakoor, Siamak Shakeri +4
Optimal selection of a subset of items from a given set is a hard problem that requires combinatorial optimization. In this paper, we propose a subset selection algorithm that is t…
Quasi-hyperbolic momentum and Adam for deep learning
Jerry Ma, Denis Yarats
Momentum-based acceleration of stochastic gradient descent (SGD) is widely used in deep learning. We propose the quasi-hyperbolic momentum algorithm (QHM) as an extremely simple al…
Learning to Perform Local Rewriting for Combinatorial Optimization
Xinyun Chen, Yuandong Tian
Search-based methods for hard combinatorial optimization are often guided by heuristics. Tuning heuristics in various conditions and situations is often time-consuming. In this pap…
A theoretical framework for deep locally connected ReLU network
Yuandong Tian
Understanding theoretical properties of deep and locally connected nonlinear network, such as deep convolutional neural network (DCNN), is still a hard problem despite its empirica…
Not Just Privacy: Improving Performance of Private Deep Learning in Mobile Cloud
Ji Wang, Jianguo Zhang, Weidong Bao +3
The increasing demand for on-device deep learning services calls for a highly efficient manner to deploy deep neural networks (DNNs) on mobile devices with limited capacity. The cl…
Backplay: "Man muss immer umkehren"
Cinjon Resnick, Roberta Raileanu, Sanyam Kapoor +3
Model-free reinforcement learning (RL) requires a large number of trials to learn a good policy, especially in environments with sparse rewards. We explore a method to improve the…
Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees
Yuping Luo, Huazhe Xu, Yuanzhi Li +3
Model-based reinforcement learning (RL) is considered to be a promising approach to reduce the sample complexity that hinders model-free RL. However, the theoretical understanding…
Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes
Ronan Fruit, Matteo Pirotta, Alessandro Lazaric
While designing the state space of an MDP, it is common to include states that are transient or not reachable by any policy (e.g., in mountain car, the product space of speed and p…
Mixed batches and symmetric discriminators for GAN training
Thomas Lucas, Corentin Tallec, Jakob Verbeek +1
Generative adversarial networks (GANs) are pow- erful generative models based on providing feed- back to a generative network via a discriminator network. However, the discriminato…
JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
Yunchen Pu, Shuyang Dai, Zhe Gan +5
A new generative adversarial network is developed for joint distribution matching. Distinct from most existing approaches, that only learn conditional distributions, the proposed m…
Randomized Value Functions via Multiplicative Normalizing Flows
Ahmed Touati, Harsh Satija, Joshua Romoff +2
Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimensional state and action spaces. Unlike t…
NAM: Non-Adversarial Unsupervised Domain Mapping
Yedid Hoshen, Lior Wolf
Several methods were recently proposed for the task of translating images between domains without prior knowledge in the form of correspondences. The existing methods apply adversa…
Unsupervised Alignment of Embeddings with Wasserstein Procrustes
Edouard Grave, Armand Joulin, Quentin Berthet
We consider the task of aligning two sets of points in high dimension, which has many applications in natural language processing and computer vision. As an example, it was recentl…
Classifier-agnostic saliency map extraction
Konrad Zolna, Krzysztof J. Geras, Kyunghyun Cho
Currently available methods for extracting saliency maps identify parts of the input which are the most important to a specific fixed classifier. We show that this strong dependenc…
Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search
Linnan Wang, Yiyang Zhao, Yuu Jinnai +2
Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires…
Conditional molecular design with deep generative models
Seokho Kang, Kyunghyun Cho
Although machine learning has been successfully used to propose novel molecules that satisfy desired properties, it is still challenging to explore a large chemical space efficient…
Can recurrent neural networks warp time?
Corentin Tallec, Yann Ollivier
Successful recurrent models such as long short-term memories (LSTMs) and gated recurrent units (GRUs) use ad hoc gating mechanisms. Empirically these models have been found to impr…
Understanding the Loss Surface of Neural Networks for Binary Classification
Shiyu Liang, Ruoyu Sun, Yixuan Li +1
It is widely conjectured that the reason that training algorithms for neural networks are successful because all local minima lead to similar performance, for example, see (LeCun e…