activity
20182021
most citedQKD: Quantization-aware Knowledge Distillation

47 citations · 83 across the 4 of their papers we have counts for

collaborators

8 papers

cs.NE2021

Data-driven Weight Initialization with Sylvester Solvers

Debasmit Das, Yash Bhalgat, Fatih Porikli

In this work, we propose a data-driven scheme to initialize the parameters of a deep neural network. This is in contrast to traditional approaches which randomly initialize paramet…

cs.CV2020

Structured Convolutions for Efficient Neural Network Design

Yash Bhalgat, Yizhe Zhang, Jamie Lin +1

In this work, we tackle model efficiency by exploiting redundancy in the \textit{implicit structure} of the building blocks of convolutional neural networks. We start our analysis…

cs.CV202017 cited

LSQ+: Improving low-bit quantization through learnable offsets and better initialization

Yash Bhalgat, Jinwon Lee, Markus Nagel +2

Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, w…

cs.LG2020

Learned Threshold Pruning

Kambiz Azarian, Yash Bhalgat, Jinwon Lee +1

This paper presents a novel differentiable method for unstructured weight pruning of deep neural networks. Our learned-threshold pruning (LTP) method learns per-layer thresholds vi…

cs.CV201947 cited

QKD: Quantization-aware Knowledge Distillation

Jangho Kim, Yash Bhalgat, Jinwon Lee +2

Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge…

cs.LG20193 cited

Teacher-Student Learning Paradigm for Tri-training: An Efficient Method for Unlabeled Data Exploitation

Yash Bhalgat, Zhe Liu, Pritam Gundecha +2

Given that labeled data is expensive to obtain in real-world scenarios, many semi-supervised algorithms have explored the task of exploitation of unlabeled data. Traditional tri-tr…