activity
20192022
most citedCoherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization

20 citations · 35 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2022

A Closer Look at Hardware-Friendly Weight Quantization

Sungmin Bae, Piotr Zielinski, Satrajit Chatterjee

Quantizing a Deep Neural Network (DNN) model to be used on a custom accelerator with efficient fixed-point hardware implementations, requires satisfying many stringent hardware-fri…

cs.LG202113 cited

Apollo: Transferable Architecture Exploration

Amir Yazdanbakhsh, Christof Angermueller, Berkin Akin +7

The looming end of Moore's Law and ascending use of deep learning drives the design of custom accelerators that are optimized for specific neural architectures. Architecture explor…

cs.LG2020

Logic Synthesis Meets Machine Learning: Trading Exactness for Generalization

Shubham Rai, Walter Lau Neto, Yukio Miyasaka +37

Logic synthesis is a fundamental step in hardware design whose goal is to find structural representations of Boolean functions while minimizing delay and area. If the function is c…

cs.LG20202 cited

Making Coherence Out of Nothing At All: Measuring the Evolution of Gradient Alignment

Satrajit Chatterjee, Piotr Zielinski

We propose a new metric (-coherence) to experimentally study the alignment of per-example gradients during training. Intuitively, given a sample of size , -coherence is th…

cs.LG2020

Weak and Strong Gradient Directions: Explaining Memorization, Generalization, and Hardness of Examples at Scale

Piotr Zielinski, Shankar Krishnan, Satrajit Chatterjee

Coherent Gradients (CGH) is a recently proposed hypothesis to explain why over-parameterized neural networks trained with gradient descent generalize well even though they have suf…

cs.LG202020 cited

Coherent Gradients: An Approach to Understanding Generalization in Gradient Descent-based Optimization

Satrajit Chatterjee

An open question in the Deep Learning community is why neural networks trained with Gradient Descent generalize well on real datasets even though they are capable of fitting random…