Parthe Pandit

Thakur Family Chair Assistant Professor @ C-MInDS, IIT Bombay

[Parthe Pandit @PartheP]

@gambhir_sheetal can you help us take this forward?

[Parthe Pandit @PartheP]

@mybmc No action taken on this blocked & broken drainage chamber on LJ Rd despite formal complaint, follow-ups. Please take immediate action. Serious health menace for residents. Local sewage not draining into municipal gutters ⇒ clogged sewage ⇒ rats, mosquitos, cockroaches...

[Parthe Pandit @PartheP]

@dbeagleholeCS @etienne_barnard @etienne_barnard
very good question!
here is a (hopefully satisfactory) answer:
https://t.co/qNrEvReLCP

[Daniel Beaglehole @dbeagleholeCS]

We identify that Conv Nets implement a variant of the same general mechanism of feature learning as in fully-connected networks. The covariances of the filters in CNNs again recover the average gradient outer-product (AGOP) of the model, additionally averaged over input patches.

[Parthe Pandit @PartheP]

@dbeagleholeCS @_onionesque easier to come up with new iterative algorithms rather than throwing away previous estimates

[Parthe Pandit @PartheP]

@MountainOfMoon Wow thats amazing news!! Congrats

[Parthe Pandit @PartheP]

@andrewgwils 2. https://t.co/JWiWizMMgb

How to train kernel models with large number of centers (or inducing points)?

A new algorithm, EigenPro3, to train such models requiring only O(p) memory for p centers. Prior work such as FALKON needed O(p^2) memory, ie, infeasible for large models

[Parthe Pandit @PartheP]

@andrewgwils You might find these papers interesting too:

1. https://t.co/RjwtzBG9nm

recursively adapting kernel functions inspired by how neural networks learn features

These models, Recursive Feature Machines, are SotA on tabular datasets and bridge the gap to fully connected networks

[Parthe Pandit @PartheP]

@raazdwivedi @Cornell_ORIE @cornell_tech @Cornell @LesterMackey Congratulations Raaz!! <3

[Parthe Pandit @PartheP]

@nmallinar you can't just get a single dream of Costco. you have to get a 32 pack

[Parthe Pandit @PartheP]

@PreetumNakkiran i am hoping someone creates a generative model that converts hand drawings to professional figures

[Parthe Pandit @PartheP]

@gururajS92 @JeonghyunW @Prashxnt_Nair @UBC @HpcaArchConf Congrats Guru!

[Parthe Pandit @PartheP]

We now have a simple, powerful, and stable alternative to Deep Nets

A challenge in classical kernel models is choosing the 'right' kernel

By examining NN training, we identified the modification necessary to empower kernels - FEATURE LEARNING

#NeuralNetworkFreeSince2023

[Daniel Beaglehole @dbeagleholeCS]

What is the nature of feature learning in deep networks? We propose that neural networks recover a statistic known as the average gradient outer product (AGOP).

Github: https://t.co/P5FW59VD8Y
arXiv: https://t.co/MW9Uo6nOnj

[Parthe Pandit @PartheP]

@Yizhezhu_ How many samples do I need to generate to achieve the rate? If there are n true samples, can you generate O(sqrt(n)) samples and still achieve small W1-distance?

[Parthe Pandit @PartheP]

@ysbhalgat Paragraph structure is very important for technical communication.
The same text should perhaps be divided into 3-4 separate paragraphs, each with a purpose.

[Parthe Pandit @PartheP]

@ysbhalgat Not a good summary
- Needs bullets. Currently, I need to read an entire sentence with obscure 10-word-named schemes to get to the start of the next sentence
- The Capitalization Of Words In The Sentences Makes It Harder To Read Easily
- Topics can be segregated based on themes

[Parthe Pandit @PartheP]

@_onionesque whats the difference between Bayes theorem and Bayes rule?

[Parthe Pandit @PartheP]

@ysbhalgat Why is this a good summarization?

[Rob Nowak @rdnowak]

Rahul Parhi and I wrote a tutorial style article to explain modern theory of deep learning and neural function spaces via elementary signal/image processing concepts (Fourier transform, Radon transform, L1 regularization, sparsity) https://t.co/nDsmX2L6XI

[Parthe Pandit @PartheP]

@DimitrisPapail the difference between
"I could have written that" v/s "I can't paint that" ?