←
Abhishek Shetty159 posts
Abhishek Shetty avatar

Abhishek Shetty

@AShettyV

asst prof at @gatech_scs FODSI Postdoctoral Fellow @MIT PhD from @Berkeley_EECS; Ex: Microsoft Research, Apple Apple AI/ML Research Fellow 2023

◷ Joined February 2020
Peter Li avatar
⟳ Abhishek Shetty retweeted
Peter Li@lipet2k·Nov 16

4/ Joint work with my wonderful collaborators: Lunjia Hu, Anish Jayant, Princewill Okoroafor, and Abhishek Shetty. The animation was very much inspired by @TED_ED (minus the silky narrator voice) and @3blue1brown. Grant’s recent IAS talk convinced me that exposition will play a central role in understanding TCS and math going forward :)

Peter Li avatar
⟳ Abhishek Shetty retweeted
Peter Li@lipet2k·Nov 16

2/ Using the language of communication complexity, an encoder sees x ~ D and writes down b bits. Later, a decoder receives a task f from a class F, and has to predict f(x) using those bits, with error ≤ ε. Our work shows that O(d* log(1/ε)) bits suffice (where d* is the dual Vapnik-Chervonenkis dimension) with a deterministic encoder, which is worst-case optimal. The key idea in our upper bound is a potential function argument, where we compare the entropy gained from each greedy feature selection with the number of patterns allowed by the dual VC dimension.

Peter Li avatar
⟳ Abhishek Shetty retweeted
Peter Li@lipet2k·Nov 16

1/ How much information must a representation keep to accurately answer every question in a task family? Motivated by the notion of features from ML, we study the complexity of representing data that allows for downstream evaluation with a given family of functions.

5:50
Jacob Hilton avatar
⟳ Abhishek Shetty retweeted
Jacob Hilton@JacobHHilton·Oct 16

Language models are getting much, much harder to fully understand with scale, not easier! (Thread)

Hey @nickcammarata, have you interpreted my 432-parameter model yet? Do you think you'll manage it by year end? That's 4 hours per parameter

Post attachment
Jelani Nelson avatar
⟳ Abhishek Shetty retweeted
Jelani Nelson@minilek·Oct 12

Morgenstern’s lower bound (and Ailon’s) is only for linear algorithms, so that leaves open the possibility that nonlinear algorithms that are numerically stable could beat n log n. Morgenstern says so himself. OAI doesn’t resolve this, but it’s incorrect to say the problem is settled.

Post attachment
Vinod Vaikuntanathan avatar
⟳ Abhishek Shetty retweeted
Vinod Vaikuntanathan@Vinod_MIT·Oct 10

If the frontier labs ran their internal models to break cryptography (of the most important kind, like AES, SHA, RSA, ECDL, LWE and Module-LWE) with N tokens for D days and it did *not* work, that would be an extremely useful piece of information to know at this point. To calm the markets, if you will. (On the other hand, if it did work, that's ... interesting ... too, but it's an entirely different story.) Of course, this is all with the understanding that these bits might change in M months.

Hanlin Ren avatar
⟳ Abhishek Shetty retweeted
Hanlin Ren@dfc7027894e168c·Oct 9

Thoughts: Given the recent advance in math, many "standard" (e.g., number-theoretic / lattice) assumptions are threatened. We need public-key encryption (and other crypto) with *universal* security --- if *any* secure PKE exists, our PKE is secure. (1/2)

Nika Haghtalab avatar
⟳ Abhishek Shetty retweeted
Nika Haghtalab@nhaghtal·Oct 9

2/n Inference serving has been central to making LLMs faster and more efficient. But when compute is scarce, deciding whose request gets served first still largely comes down to a handful of priority tiers --- a pretty coarse and blunt tool that doesn't really let users express how sensitive their requests are to latency. A coding agent waiting for its next response, someone interacting with an LLM in real time, and my long-running overnight research queries certainly don't have the same latency needs!

Nika Haghtalab avatar
⟳ Abhishek Shetty retweeted
Nika Haghtalab@nhaghtal·Oct 9

1/n What should the economic layer on top of LLM inference serving platforms look like? In our new paper, Inference Auctions, we show how to bring economic considerations into the design of inference systems, rather than treating resource allocation and systems efficiency as separate problems. This is a joint work with @keegan_w_harris @sidpra5ad @ashertrockman and Mike Jordan.

Post attachment

Check out our new paper on Inference Auctions! We also design inference auction autobidders, which allow a user to specify an inference budget and dynamically adjusts its bids over time to maximize user utility subject to the budget constraint.

Sitan Chen avatar
⟳ Abhishek Shetty retweeted
Sitan Chen@sitanch·Oct 9

🚨 Thrilled to be co-organizing a Simons Institute semester-long program on diffusions and flows with @joanbruna, Sinho Chewi, @KonstDaskalakis, @ArnaudDoucet1 in Fall '27! The call for Simons postdoctoral research fellowships for the program is out now, more info below ⬇️ 1/3

Jason Lee avatar
⟳ Abhishek Shetty retweeted
Jason Lee@jasondeanlee·Oct 9

Come join us at simons. Best place for theorists!

🚨 Thrilled to be co-organizing a Simons Institute semester-long program on diffusions and flows with @joanbruna, Sinho Chewi, @KonstDaskalakis, @ArnaudDoucet1 in Fall '27! The call for Simons postdoctoral research fellowships for the program is out now, more info below ⬇️ 1/3