Krishna Pillutla @KrishnaPillutla Twitter profile

Pinned Tweet

Krishna Pillutla

6 months

I’m thrilled to announce that I'll be joining @iitmadras as an Assistant Professor in April 2024! I’m immensely grateful to my amazing mentors, family, and friends for their unwavering support. (1/4)

49

58

2K

Last Seen Profiles

@LiteLLM

@NakahooSe

@westemwind

@PurdyKurty

@StalkingVi96051

@CasinoCoin

@JaneotN

@MADOKA87FORMER

@Lux_Ferer

@PNLMusic

@PetraLaiti

@TBarLavi

@LizzieStyx

@mikeahorton

@flathom_jkt

@kwprayernetwork

@defiexperts

@ChineseEmbinUS

@Mustbethehawk

@FishermansFilm

@MadamWanderBeki

@STONE_and_MONEY

@LauraleeB4real

@MarkOtabor

@SirZackMorris

@NordoniaSchools

@PowPowChaos

@FrancoisArnoux

@SWavestore

@MansourSorosoro

@RealRodrigoPolo

@durian08263

@patraniaga

@Lyrayne1

@trinidijanai

@Coach_Mulford

Krishna Pillutla

@KrishnaPillutla

3 years

How can we measure the gap between machine text and human text? We introduce MAUVE, a new comparison measure for open-ended text generation, in our upcoming oral presentation at NeurIPS 2021. Paper: Pip package: 1/n

3

75

301

Krishna Pillutla

@KrishnaPillutla

3 years

Honored to receive the Outstanding Paper Award at NeurIPS 2021 for MAUVE with the wonderful @swabhz @rown @jwthickstun @wellecks @YejinChoinka and Zaid Harchoaui!

Gautam Kamath

@thegautamkamath

3 years

Outstanding Paper Award 4. MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers, by @KrishnaPillutla , @swabhz , @rown , @jwthickstun , @wellecks , @YejinChoinka , Zaid Harchaoui (4/n)

5

21

107

4

14

168

Krishna Pillutla

@KrishnaPillutla

6 months

Returning home to India and contributing to the nation's vibrant academic community fills me with immense gratitude and excitement. I look forward to collaborating with talented students and researchers to make a positive impact. (3/4)

2

8

161

Krishna Pillutla

@KrishnaPillutla

6 months

I'll be building a new group focusing on the theory and practice of ML & AI research, exploring exciting areas like: - Privacy-preserving ML & federated learning - Robust & generalizable models and their optimization - Generative AI, LLMs, and their applications (2/4)

2

5

86

Krishna Pillutla

@KrishnaPillutla

6 months

If you're interested in joining my group or collaborating, please feel free to contact me! I’ll also be at #NeurIPS in person and am happy to chat! (4/4) #IITMadras #Research @iitmcse

8

7

82

Krishna Pillutla

@KrishnaPillutla

2 months

Calling motivated students interested in pursuing MS/PhD in ML/AI, specifically privacy & generative AI! The research group I'm starting at @iitmadras has openings! Apply by *Mar 31* directly to @DSAI_IITM or @iitmcse at !

Dept. of Data Science & AI, IIT Madras

@DSAI_IITM

3 months

Our MS/PhD Applications are now open! Apply before 🗓️31st March! #PhDposition #MS #Research - for more info on our research areas, see - We have a number of exciting research centres @WSAI_IITM @cerai_iitm @IBSE_IITM @ai4bharat

1

13

26

0

25

67

Krishna Pillutla

@KrishnaPillutla

2 years

We just released a new Python package! Fast and differentiable geometric median in PyTorch and NumPy. Github: Install: pip install geom-median 1/3

1

6

39

Krishna Pillutla

@KrishnaPillutla

2 years

Excited to present our work "Federated Learning with Partial Model Personalization" at @icmlconf #ICML2022 ! Poster: Thu 7/21, 6-8 pm EDT in Hall E #724 Spotlight: Thu 7/21, 4:40 pm in Hall G (Applications/Optim.) 1/n

1

4

26

Krishna Pillutla

@KrishnaPillutla

6 months

Interested in how federated learning scales to foundation models? Concerned about how we do not have suitably large federated / group-partitioned / user-stratified datasets? We got you covered at #NeurIPS poster #1217 at 5 pm today (Thursday).

Zachary Charles

@MatharyCharles

10 months

1/ Our work is out! 🚨 Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning We push federated learning research closer to LLM scales. Paper: Joint with @nicki_mitch & @KrishnaPillutla Thread below.

1

10

54

1

2

18

Krishna Pillutla

@KrishnaPillutla

6 months

Aditya is among the most dedicated and passionate researchers I know. He cares deeply about being a good mentor. Aditya will be a wonderful professor!

Aditya Kusupati

@adityakusupati

6 months

📢📢At the last minute, I decided to go on the job market this year!!! Grateful for RTs & promotion at your univ.😇 CV & Statements: Will be at #NeurIPS2023 ! presenting AdANNS, Priming, Objaverse & MADLAD. DM if you are around, would love to catch up👋

2

49

182

0

14

Krishna Pillutla

@KrishnaPillutla

3 years

In a related NeurIPS 2021 paper led by @UWStat grad student Lang Liu, we also study the theory of MAUVE and divergence frontier methods in general. More details on this are coming up shortly. Paper: 8/8

0

3

11

Krishna Pillutla

@KrishnaPillutla

10 months

Super excited about our recent work on federated foundation models! - New LLM-scale federated datasets (+ software to create your own from TFDS and @huggingface datasets) - Federated training of a GPT-2-sized LM (from scratch) shows meta-learning!

Zachary Charles

@MatharyCharles

10 months

1/ Our work is out! 🚨 Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning We push federated learning research closer to LLM scales. Paper: Joint with @nicki_mitch & @KrishnaPillutla Thread below.

1

10

54

0

2

9

Krishna Pillutla

@KrishnaPillutla

6 months

Google Research India has an incredible pre-doc program! See below for details

Divy Thakkar

@divy93t

6 months

If you're a graduating / recent undergrad /MS and you'd like to spend two years learning from the best, experimenting and creating large-scale impact - come join our Predoctoral Researcher Program. Apply before Dec 18!

6

28

159

0

8

Krishna Pillutla

@KrishnaPillutla

3 years

Hope to see you at the NeurIPS oral session on Tue Dec 07 12:00 AM -- 12:15 AM (PST) 7/n

1

8

Krishna Pillutla

@KrishnaPillutla

6 months

Ankush is incredible! Please consider applying, the deadline is Dec. 15.

Ankush Das

@Das8Ankush

6 months

Thrilled to share that I will start a tenure-track assistant professor position in the CS department at Boston University! I am looking for PhD students in the area of programming languages with applications to distributed systems, cryptography, and machine learning.

15

29

215

0

7

Krishna Pillutla

@KrishnaPillutla

3 years

Work with co-authors from @uwcse @UWStat and @allen_ai : @swabhz @rown @jwthickstun @wellecks @YejinChoinka and Zaid Harchaoui 2/n

1

0

6

Krishna Pillutla

@KrishnaPillutla

3 years

Given neural text and human text, MAUVE yields a scalar measure of the gap between them. It directly compares the learnt distribution from a text generation model to the distribution of human-written text using information divergence frontiers. 3/n

1

0

6

Krishna Pillutla

@KrishnaPillutla

3 years

Finally, we show that MAUVE correlates better with human judgments compared to existing metrics for evaluating generations, e.g. generation perplexity, Self-BLEU, Jensen-Shannon divergence 6/n

1

0

6

Krishna Pillutla

@KrishnaPillutla

1 month

I'll be at #ICLR at these posters: Correlated Noise Provably Beats Independent Noise for Differentially Private Learning ( #217 @ 4:30 pm on Wednesday) Distributionally Robust Optimization with Bias and Variance Reduction (Spotlight, #154 @ 10:45 am on Thursday)

1

0

5

Krishna Pillutla

@KrishnaPillutla

2 years

The geometric median, a multivariate generalization of the median, is similarly robust to outliers. It needs to be computed numerically via convex optimization. Package features: * GPU support (PyTorch only) * Compatible w/ backprop (PyTorch only) * Blazing fast algorithm 2/3

1

0

5

Krishna Pillutla

@KrishnaPillutla

3 years

This captures two types of errors: (I) where the model assigns high probability to sequences which do not resemble human-written text, and (II) where the model distribution does not cover the human distribution, i.e., it fails to yield diverse samples. 4/n

1

0

5

Krishna Pillutla

@KrishnaPillutla

3 years

We empirically show that MAUVE is able to quantify known properties of generated text with respect to text length, model size, and decoding more correctly and with fewer restrictions than existing distributional evaluation metrics. 5/n

1

0

5

Krishna Pillutla

@KrishnaPillutla

2 years

Through extensive experiments, we find that the best layers to personalize are based on the diversity in the task. * next word pred.: diverse outputs => personalize output layer * speech: diverse inputs => personalize input layer * label skew => architectural solutions 6/n

1

0

4

Krishna Pillutla

@KrishnaPillutla

2 years

We applied the geometric median for federated learning in our paper . At the time, we did not find any Python package for the geometric median. We open-sourced this package to fill the gap. Hope you find it useful!

Robust Aggregation for Federated Learning

Federated learning is the centralized training of statistical models from decentralized data on mobile devices while preserving the privacy of each device. We present a robust aggregation approach...

arxiv.org

0

4

Krishna Pillutla

@KrishnaPillutla

2 years

Hope to see you at the ICML at the talk/poster or drop me a line! Code: 7/7

GitHub - facebookresearch/FL_partial_personalization: Federated Learning with Partial Model...

Federated Learning with Partial Model Personalization - facebookresearch/FL_partial_personalization

github.com

0

3

Krishna Pillutla

@KrishnaPillutla

2 months

@ravi_iitm @rbc_dsai_iitm @iitmadras @DSAI_IITM Thank you! 🙏

0

3

Krishna Pillutla

@KrishnaPillutla

2 years

Work with co-authors from @MetaAI : Kshitiz Malik, @AbdoMohamedML , Michael Rabbat, Maziar Sanjabi, Lin Xiao 2/n

1

0

3

Krishna Pillutla

@KrishnaPillutla

2 years

Empirically, we also find that the alternating update algorithm is better by a small but consistent margin. 5/n

1

0

2

Krishna Pillutla

@KrishnaPillutla

6 months

@divy93t @iitmadras Thank you, Divy! 😃

0

2

Krishna Pillutla

@KrishnaPillutla

2 years

We compare 2 local update algos from previous work. We establish 1/sqrt(t) rates for both in the smooth nonconvex case but alternating update of personal and shared params has better constants. Its analysis is also technically challenging due to dependent random variables. 4/n

1

0

2

Krishna Pillutla

@KrishnaPillutla

2 years

We study personalizing a few layers of the model. We have (1) convergence theory of optimization algorithms for personalized federated learning, (2) extensive empirical experiments in text, vision, and speech 3/n

1

0

2

Krishna Pillutla

@KrishnaPillutla

6 months

Excited to present our work “Unleashing the Power of Randomization in Auditing Differentially Private ML” at #NeurIPS at poster #1609 at 10:45 am today (Thursday). Joint w/ Galen Andrew, @KairouzPeter , Brendan McMahan, @AlinaMOprea , @sewoong79 (1/n)

1

2

Krishna Pillutla

@KrishnaPillutla

6 months

There are several interesting technical details, including: - a bias-variance trade-off for random canaries! - our very own novel concentration inequalities! - lots of cool math! See you at the poster or drop me a line for more details! (5/n)

1

0

2

Krishna Pillutla

@KrishnaPillutla

25 days

@adityakusupati @BloodworksNW I faced it many times across several US cities, seems to be standard procedure. Not sure I understand this logic though

0

1

Krishna Pillutla

@KrishnaPillutla

6 months

@apsarathchandar @iitmadras Thank you Sarath! I would to chat, taking this to email :)

0

2

Krishna Pillutla

@KrishnaPillutla

6 months

@amritsinghbedi3 @EkanshVerma12 @iitmadras Thank you so much, Amrit! Heartiest congratulations to you in return :)

1

0

1

Krishna Pillutla

@KrishnaPillutla

1 month

@bksalimi @NSF @HDSIUCSD @GuptaUcsd Congratulations, Babak!

0

1

Krishna Pillutla

@KrishnaPillutla

6 months

@thegautamkamath Thank you, Gautam!

0

1

Krishna Pillutla

@KrishnaPillutla

6 months

@danish037 @iitmadras Thank you, Danish ❣️

0

1

Krishna Pillutla

@KrishnaPillutla

3 years

@sewoong79 @swabhz @rown @jwthickstun @YejinChoinka Thank you, Sewoong! 🙂

0

1

Krishna Pillutla

@KrishnaPillutla

6 months

@dhumchikdish @iitmadras Thank you, Anirudh!

0

1

Krishna Pillutla

@KrishnaPillutla

10 days

@ramyavinayak @iitmadras Thanks for the wonderful talk, Ramya! I'm looking forward to your next visit :)

0

1

Krishna Pillutla

@KrishnaPillutla

6 months

@SameerMalladi @iitmadras Thank you, Sameer!

0

1

Krishna Pillutla

@KrishnaPillutla

6 months

@KanishakKataria @iitmadras Thank you so much, Kanishak! :)

0

1

Krishna Pillutla

@KrishnaPillutla

1 month

More details about each paper in their respective threads. Please come by and say hi (or reach out and I'd be happy to chat)!

0

1

Krishna Pillutla

@KrishnaPillutla

10 days

@HongyiWang10 @RutgersCS Heartiest congratulations, @HongyiWang10 !

0

1

Krishna Pillutla

@KrishnaPillutla

6 months

@MeiyappanL @iitmadras Thank you, @MeiyappanL ! I'm looking forward to it :)

0

1

Krishna Pillutla

@KrishnaPillutla

3 years

@crwhite_ml @thegautamkamath @swabhz @rown @jwthickstun @wellecks @YejinChoinka Thank you, Colin! 🙂

0

1

Krishna Pillutla

@KrishnaPillutla

2 years

@agarwl_ @swabhz @rown @jwthickstun @wellecks @YejinChoinka Thank you so much and heartiest congratulations to you as well! :)

0

1

Krishna Pillutla

@KrishnaPillutla

1 month

Excited to present our work “Correlated Noise Provably Beats Independent Noise for Differentially Private Learning” at #ICLR at poster #217 at 4:30 pm today (Wednesday). Joint w/ @Chris_Choquette @DjDvij , @aroonganesh , @shortstein , Abhradeep Thakurta (1/n)

1

0

1