b'Hanlin Tang'

research

∙ 03/25/2022

MKQ-BERT: Quantized BERT with 4-bits Weights and Activations

Recently, pre-trained Transformer based language models, such as BERT, h...

0 Hanlin Tang, et al. ∙

research

∙ 08/04/2021

ErrorCompensatedX: error compensation for variance reduced algorithms

Communication cost is one major bottleneck for the scalability for distr...

0 Hanlin Tang, et al. ∙

research

∙ 05/30/2021

On the geometry of generalization and memorization in deep neural networks

Understanding how large neural networks avoid memorizing training data i...

0 Cory Stephenson, et al. ∙

research

∙ 04/15/2021

Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models

While vector-based language representations from pretrained language mod...

0 Matteo Alleman, et al. ∙

research

∙ 04/13/2021

1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed

To train large models (like BERT and GPT-3) with hundreds or even thousa...

0 Conglong Li, et al. ∙

research

∙ 02/04/2021

1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed

Scalable training of large models (like BERT and GPT-3) requires careful...

0 Hanlin Tang, et al. ∙

research

∙ 08/26/2020

APMSqueeze: A Communication Efficient Adam-Preconditioned Momentum SGD Algorithm

Adam is the important optimization algorithm to guarantee efficiency and...

11 Hanlin Tang, et al. ∙

research

∙ 07/14/2020

Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning

As modern neural networks have grown to billions of parameters, meeting ...

19 Shauharda Khadka, et al. ∙

research

∙ 06/01/2020

Emergence of Separable Manifolds in Deep Language Representations

Deep neural networks (DNNs) have shown much empirical success in solving...

0 Jonathan Mamou, et al. ∙

research

∙ 03/03/2020

Untangling in Invariant Speech Recognition

Encouraged by the success of deep neural networks on a variety of visual...

0 Cory Stephenson, et al. ∙

research

∙ 01/16/2020

Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks

Training with larger number of parameters while keeping fast iterations ...

0 Léopold Cambier, et al. ∙

research

∙ 11/19/2019

Mimic The Raw Domain: Accelerating Action Recognition in the Compressed Domain

Video understanding usually requires expensive computation that prohibit...

0 Barak Battash, et al. ∙

research

∙ 11/06/2019

MLPerf Inference Benchmark

Machine-learning (ML) hardware and software system demand is burgeoning....

27 Vijay Janapa Reddi, et al. ∙

research

∙ 10/11/2019

Central Server Free Federated Learning over Single-sided Trust Social Networks

Federated learning has become increasingly important for modern machine ...

0 Chaoyang He, et al. ∙

research

∙ 10/02/2019

Using Image Priors to Improve Scene Understanding

Semantic segmentation algorithms that can robustly segment objects acros...

46 Brigit Schroeder, et al. ∙

research

∙ 10/02/2019

MLPerf Training Benchmark

Machine learning is experiencing an explosion of software and hardware s...

6 Peter Mattson, et al. ∙

research

∙ 09/19/2019

Triplet-Aware Scene Graph Embeddings

Scene graphs have become an important form of structured knowledge for t...

0 Brigit Schroeder, et al. ∙

research

∙ 07/17/2019

DeepSqueeze: Decentralization Meets Error-Compensated Compression

Communication is a key bottleneck in distributed training. Recently, an ...

0 Hanlin Tang, et al. ∙

research

∙ 07/17/2019

DeepSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression

Communication is a key bottleneck in distributed training. Recently, an ...

0 Hanlin Tang, et al. ∙

research

∙ 06/26/2019

Generalization to Novel Objects using Prior Relational Knowledge

To solve tasks in new environments involving objects unseen during train...

0 Varun Kumar Vijay, et al. ∙

research

∙ 06/13/2019

Amur Tiger Re-identification in the Wild

Monitoring the population and movements of endangered species is an impo...

4 Shuyuan Li, et al. ∙

research

∙ 05/15/2019

DoubleSqueeze: Parallel Stochastic Gradient Descent with Double-Pass Error-Compensated Compression

A standard approach in large scale machine learning is distributed stoch...

0 Hanlin Tang, et al. ∙

research

∙ 04/19/2019

Compact Scene Graphs for Layout Composition and Patch Retrieval

Structured representations such as scene graphs serve as an efficient an...

0 Subarna Tripathi, et al. ∙

research

∙ 03/28/2019

SpaceNet MVOI: a Multi-View Overhead Imagery Dataset

Detection and segmentation of objects in overheard imagery is a challeng...

0 Nicholas Weir, et al. ∙

research

∙ 01/11/2019

Using Scene Graph Context to Improve Image Generation

Generating realistic images from scene graphs asks neural networks to be...

6 Subarna Tripathi, et al. ∙

research

∙ 10/17/2018

Distributed Learning over Unreliable Networks

Most of today's distributed machine learning systems assume reliable ne...

0 Hanlin Tang, et al. ∙

research

∙ 03/19/2018

D^2: Decentralized Training over Decentralized Data

While training a machine learning model using multiple workers, each of ...

0 Hanlin Tang, et al. ∙

research

∙ 03/17/2018

Decentralization Meets Quantization

Optimizing distributed learning systems is an art of balancing between c...

0 Hanlin Tang, et al. ∙

research

∙ 06/07/2017

Recurrent computations for visual pattern completion

Making inferences from partial information constitutes a critical aspect...

0 Hanlin Tang, et al. ∙

Hanlin Tang

Featured Co-authors