Some reviews on theory papers at ICML make me want to hug the reviewer and telling them "I am so sorry, you don't understand the basics of this topic..."
Theory → Practice 📈
• Provable efficient algorithms
• Works with standard ANN systems
• Strong empirical gains in diversity while maintaining relevance in several real-world datasets
Joint work with @BarmanSiddharth, @shivi98g & @KShiragur.
See you at ICLR 2026 in Rio 🇧🇷
🎉 Our paper accepted at ICLR 2026!
We study the backbone of applications like search, recommendation, & RAG: “Nearest Neighbor Search.”
But instead of optimizing only relevance, we ask
👉 Can we balance relevance & diversity in a principled way?
Paper: https://t.co/evbrj5ahTP
Prior work: diversity via hard constraint→not query-dependent
Our insight:
📐 View attributes (seller, color, brand) as “agents”
⚖️ Nash Social Welfare to balance relevance & diversity
Result: query-dependent solution.
“shirts” → diverse results 🌈
“blue shirt” → all blue 🔵
Drop by our posters to talk about imperfect data and responsible AI. @stochastic_nir is seeking a PhD position this year, and I am seeking postdoctoral opportunities. (3/3)
2. Cost-Efficient Fairness Audit Under Partial Feedback (https://t.co/6D1jUeDnQ0), at the Reliable ML (Sat 6 Dec 4 p.m. — 5 p.m. PST) and Regulatable ML workshop (Sun 7 Dec 8 a.m.— 5 p.m. PST). Led by @stochastic_nir , with Praharsh Nanavati, @KShiragur and Amit Deshpande.(2/3)
There *may* be some collusion, but how prevalent is this? Maybe a few papers, maybe a hundred?
Clearly not enough to revert the whole ICLR discussion phase! Plus, organizers can closely track papers where the scores jumped drastically.
Thrilled that our paper https://t.co/PQmerlclNe will be presented by Amit Deshpande (MSRI) as poster @ 𝐍𝐞𝐮𝐫𝐈𝐏𝐒 𝟐𝟎𝟐𝟓 Workshop on Reliable ML from Unreliable Data! 🚀
Visit our poster on Dec 6 to know about this exciting work!
#NeurIPS2025#FairML#ResponsibleAI
We give:
• A realistic cost model for acquiring labels
• Near-optimal audit algorithms in black-box
• Cost-improved algo for mixture-model settings
• Empirically ~50% lower audit cost vs. natural baselines
• Extends to many fairness metrics
@Ramneet_Singhh Could you isolate that the error is due to the minted package? Couple of months back we had a hard time because of some bibliography style error. Changed from alpha to natbib and everything worked.
The Summer School on Approximation Algorithms 2025 will be held at CSA 104, IISc, from 21st to 25th May 2025. This event is targeted towards postgraduate and senior undergraduate students. We are accepting applications till 25th March 2025.
It was an awesome course! Thoroughly enriching. Please check out the course webpage for the amazing resources curated by Prof @arindamkhan and Prof @BarmanSiddharth .
Travelling to @AshokaUniv to attend exSPLORe2025 workshop (https://t.co/PrZrTe3r7y) from 14th to 18th January. Looking forward to learning and interacting with researchers and fellow students.
@lokeshbag67 One of the most bizarre (in a thought-provoking way) I have watched so far. Yorgos has gone back to his "Dogtooth" self, may be even more.