Papers
Browse academic papers referenced in production code
Empirical Study of Off-Policy Policy Evaluation for Reinforcement Learning
We offer an experimental benchmark and empirical study for off-policy policy evaluation (OPE) in reinforcement learning, which is a key problem in many safety critical applications. Given the increasing interest in deploying learning-based methods, t...
Root Mean Square Layer Normalization
Layer normalization (LayerNorm) has been successfully applied to various deep neural networks to help stabilize training and boost model convergence because of its capability in handling re-centering and re-scaling of both inputs and weight matrix. H...
A Robust and Efficient Implementation of LOBPCG.
Locally Optimal Block Preconditioned Conjugate Gradient (LOBPCG) is widely\nused to compute eigenvalues of large sparse symmetric matrices. The algorithm\ncan suffer from numerical instability if it is not implemented with care. This\nis especially p...
Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks.
In recent years, electroencephalogram (EEG) e-motion recognition has been becoming an emerging field in artificial intelligence area, which can reflect the relation between emotional states and brain activity. In this paper, we designed a novel archi...
Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions
Deep learning models with convolutional and recurrent networks are now ubiquitous and analyze massive amounts of audio, image, video, text and graph data, with applications in automatic translation, speech-to-text, scene understanding, ranking user p...
Soft-NMS -- Improving Object Detection With One Line of Code
Non-maximum suppression is an integral part of the object detection pipeline. First, it sorts all detection boxes on the basis of their scores. The detection box M with the maximum score is selected and all other detection boxes with a significant ov...
Categorical Reparameterization with Gumbel-Softmax
Categorical variables are a natural choice for representing discrete structure in the world. However, stochastic neural networks rarely use categorical latent variables due to the inability to backpropagate through samples. In this work, we present a...
Prioritized Experience Replay
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...
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks.
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is transcribed into words or sub-word units. Recurrent neural networks (R...
A BLOCK ORTHOGONALIZATION PROCEDURE WITH CONSTANT SYNCHRONIZATION REQUIREMENTS
We propose an alternative orthonormalization method that computes the orthonormal basis from the right singular vectors of a matrix. Its advantage are: a) all operations are matrix-matrix multiplications and thus cache-efficient, b) only one synchron...
Chakra: Advancing Performance Benchmarking and Co-design using Standardized Execution Traces
Benchmarking and co-design are essential for driving optimizations and innovation around ML models, ML software, and next-generation hardware. Full workload benchmarks, e.g. MLPerf, play an essential role in enabling fair comparison across different ...
Efficient ConvBN Blocks for Transfer Learning and Beyond
Convolution-BatchNorm (ConvBN) blocks are integral components in various computer vision tasks and other domains. A ConvBN block can operate in three modes: Train, Eval, and Deploy. While the Train mode is indispensable for training models from scrat...
On the Reliability of Watermarks for Large Language Models
As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. Watermarking is a simple and effective strategy for mitigating such harms by enabling the detection and do...
Zero Bubble Pipeline Parallelism
Pipeline parallelism is one of the key components for large-scale distributed training, yet its efficiency suffers from pipeline bubbles which were deemed inevitable. In this work, we introduce a scheduling strategy that, to our knowledge, is the fir...
Exoshuffle: An Extensible Shuffle Architecture
Shuffle is one of the most expensive communication primitives in distributed data processing and is difficult to scale. Prior work addresses the scalability challenges of shuffle by building monolithic shuffle systems. These systems are costly to dev...
RL4ReAl: Reinforcement Learning for Register Allocation
We aim to automate decades of research and experience in register allocation, leveraging machine learning. We tackle this problem by embedding a multi-agent reinforcement learning algorithm within LLVM, training it with the state of the art technique...
Denoising Diffusion Implicit Models
Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps to produce a sample. To accelerate sampling, we present denoising dif...
Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs.
We present a new approach for the approximate K-nearest neighbor search based on navigable small world graphs with controllable hierarchy (Hierarchical NSW, HNSW). The proposed solution is fully graph-based, without any need for additional search str...