Anand K Subramanian



Articles

5 Feb 2024

Olafur Eliasson @ Azabudai Hills Gallery

A trip to Olafur Eliasson's exhibition at Azabudai Hills Gallery, Tokyo

#art #experience #photoessay #japan #தமிழ்

4 Aug 2023

Mathematics of Changing One's Mind

A guide to updating probabilistic beliefs using Jeffrey's rule and Pearl's method.

#math #ml #probability

4 Jul 2023

Scalene - A Python Profiler Case Study

A short note of ideas used in the high-performance python profiler - Scalene

#python #profiling #memory

29 Aug 2022

Improving the RANSAC Algorithm

Discussion about the MAGSAC algorithm, addressing a crucial hyperparameter selection issue for the RANSAC algorithm.

#math #ml #code #jax

29 Jun 2022

The Back-Gradient Trick

Stochastic Gradient Descent can be (kind of) reversed and can be used to compute gradients with respect to its hyperparameters.

#math #ml #gradient #graph #code #jax #deep-learning

31 May 2022

Parallelizing Kalman Filters

The associative property of Kalman (Bayesian) filters can yield a parallel algorithm in O(log N).

#math #ml #parallel #code #jax

24 Apr 2022

Linearization is All You Need for an Autodiff Library

A complete autodiff library can be written only with linearizing the computational graph.

#math #ml #gradient #graph #jax #code #deep-learning

23 Sep 2021

Fast Sample-Covariance Computation for Multidimensional Arrays

A quick discussion and a vectorized Python implementation for the computation of sample covariance matrices for multi-dimensional arrays.

#math #ml #code

30 Aug 2021

Asymmetric Numeral Systems

A tutorial on the lossless Asymmetric Numeral Systems (ANS) coding commonly used in image compression.

#math #ml #information-theory #code

14 Aug 2021

A Gödelian Argument for the Superiority of the Human Mind

A discussion of an argument that no Turing Machine can adequately mimic human cognitive abilities, following Gödel's theorems.

#philosophy #ai #math

27 Jun 2021

A Beautiful Way to Characterize Directed Acyclic Graphs

An interesting connection between the number of cycles in a digraph and its power adjacency matrix leads to a beautiful formulation for DAG constrains.

#graph #math #ml

18 Jun 2020

A Cleverer Trick on top of the Reparametrization Trick

Implicit differentiation can lead to an efficient computation of the gradient of reparametrized samples.

#math #ml #gradient #deep-learning

© 2024 Anand K Subramanian License Design Built with Franklin.jl