🤖

Machine Learning

Machine learning frameworks, algorithms, and training systems

Repositories

(7)

huggingface/transformers

19 papers

microsoft/onnxruntime

18 papers

mlflow/mlflow

0 papers

pytorch/pytorch

104 papers

ray-project/ray

52 papers

scikit-learn/scikit-learn

122 papers

tensorflow/tensorflow

95 papers

Papers

(373)
Showing 13 of 373 papers

BOHB: Robust and Efficient Hyperparameter Optimization at Scale

Stefan Falkner, Aaron Klein, Frank Hutter
2018
1 reference

Modern deep learning methods are very sensitive to many hyperparameters, and, due to the long training times of state-of-the-art models, vanilla Bayesian hyperparameter optimization is typically computationally infeasible. On the other hand, bandit-b...

Conservative Q-Learning for Offline Reinforcement Learning

Aviral Kumar, Aurick Zhou, George Tucker, Sergey Levine
2020
3 references

Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected, static dataset...

Convergence Analysis of Distributed Stochastic Gradient Descent with Shuffling

Qi Meng, Wei Chen, Yue Wang, Zhi-Ming Ma, Tie-Yan Liu
2017
1 reference

When using stochastic gradient descent to solve large-scale machine learning problems, a common practice of data processing is to shuffle the training data, partition the data across multiple machines if needed, and then perform several epochs of tra...

Horizon: Facebook's Open Source Applied Reinforcement Learning Platform

Jason Gauci, Edoardo Conti, Yitao Liang, Kittipat Virochsiri, Yuchen He, Zachary Kaden, Vivek Naraya...
2018
2 references

In this paper we present Horizon, Facebook's open source applied reinforcement learning (RL) platform. Horizon is an end-to-end platform designed to solve industry applied RL problems where datasets are large (millions to billions of observations), t...

Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization

Lisha Li, Kevin Jamieson, Giulia DeSalvo, Afshin Rostamizadeh, Ameet Talwalkar
2016
2 references

Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While recent approaches use Bayesian optimization to adaptively select configurations, we focus on speeding up random search through adaptive ...

Multi-agent Reinforcement Learning in Sequential Social Dilemmas

Joel Z. Leibo, Vinicius Zambaldi, Marc Lanctot, Janusz Marecki, Thore Graepel
2017
1 reference

Matrix games like Prisoner's Dilemma have guided research on social dilemmas for decades. However, they necessarily treat the choice to cooperate or defect as an atomic action. In real-world social dilemmas these choices are temporally extended. Coop...

NeuroCard: One Cardinality Estimator for All Tables

2020
1 reference

Query optimizers rely on accurate cardinality estimates to produce good execution plans. Despite decades of research, existing cardinality estimators are inaccurate for complex queries, due to making lossy modeling assumptions and not capturing inter...

Offline Reinforcement Learning with Implicit Q-Learning

Ilya Kostrikov, Ashvin Nair, Sergey Levine
2021
1 reference

Offline reinforcement learning requires reconciling two conflicting aims: learning a policy that improves over the behavior policy that collected the dataset, while at the same time minimizing the deviation from the behavior policy so as to avoid err...

Playing Atari with Deep Reinforcement Learning

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Mar...
2013
1 reference

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network, trained with a variant of Q-learning, whose input ...

Prioritized Experience Replay

Tom Schaul, John Quan, Ioannis Antonoglou, David Silver
2015
5 references

Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same...

Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits

Jack Parker-Holder, Vu Nguyen, Stephen Roberts
2020
2 references

Many of the recent triumphs in machine learning are dependent on well-tuned hyperparameters. This is particularly prominent in reinforcement learning (RL) where a small change in the configuration can lead to failure. Despite the importance of tuning...

Rainbow: Combining Improvements in Deep Reinforcement Learning

Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horga...
2017
3 references

The deep reinforcement learning community has made several independent improvements to the DQN algorithm. However, it is unclear which of these extensions are complementary and can be fruitfully combined. This paper examines six extensions to the DQN...

The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning

Jan Blumenkamp, Amanda Prorok
2020
1 reference

Many real-world problems require the coordination of multiple autonomous agents. Recent work has shown the promise of Graph Neural Networks (GNNs) to learn explicit communication strategies that enable complex multi-agent coordination. These works us...