Skip to content
View S-Sairam's full-sized avatar

Block or report S-Sairam

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Pinned Loading

  1. final-stage-bottleneck final-stage-bottleneck Public

    A systematic dissection of the Graph R-Learner for network causal inference, using PyTorch to benchmark Double Machine Learning (DML) with GNNs.

    Python

  2. sam-optimizer sam-optimizer Public

    This repository contains an independent, from-scratch implementation of the Sharpness-Aware Minimization (SAM) optimizer, as introduced in the ICLR 2021 paper by Foret et al.

    Python

  3. micrograd micrograd Public

    An exercise in deconstructing the "magic" of backpropagation into a clean, understandable, and functional implementation.

    Jupyter Notebook

  4. loss-landscape-calculus loss-landscape-calculus Public

    A first-principles Python implementation to numerically analyze 2D loss landscapes and visualize the failure modes of simple optimizers on pathological functions like the Rosenbrock.

    Jupyter Notebook

  5. bit-collapse-geometry bit-collapse-geometry Public

    Visualizing Hessian Spectral Collapse in Quantized Neural Networks

    Python 1

  6. quant-lens quant-lens Public

    Visualize loss landscapes and Hessian sharpness to diagnose "bit collapse" in quantized neural networks.

    Python