Sanyam Kapoor

I do normal science.

[Sanyam Kapoor @psiyumm]

@Tkaraletsos Congrats Theo!

[Micah Goldblum @micahgoldblum]

If we want to use LLMs for decision making, we need to know how confident they are about their predictions. LLMs don’t output meaningful probabilities off-the-shelf, so here’s how to do it 🧵
Paper: https://t.co/1F1B5XhgQO
Thanks @psiyumm and @gruver_nate for leading the charge!

[Ben Athiwaratkun @ben_athi]

Find us at burning man 2024 🔥

@gruver_nate @LotfiSanae @psiyumm @samuel_stanton_ @polkirichenko @Pavel_Izmailov @KuangYilun
@m_finzi @timrudner @ShikaiQiu @yucenlily @andrewgwils

[Sanyam Kapoor @psiyumm]

Most likely functions and most likely parameters that describe the data may differ. How much does this matter?

Read on to learn more in our new #NeurIPS2023 paper!

[Tim G. J. Rudner @timrudner]

When training machine learning models, should we learn most likely parameters—or most likely functions?

We investigate this question in our #NeurIPS2023 paper and made some fascinating observations!🚀

Paper: https://t.co/rOv0Aeqbe6

w/ @ShikaiQiu @psiyumm @andrewgwils

🧵1/10

[Pavel Izmailov @Pavel_Izmailov]

📢 I am recruiting Ph.D. students for my new lab at @nyuniversity! Please apply, if you want to work on understanding deep learning and large models, and do a Ph.D. in the most exciting city on earth.

Details on my website: https://t.co/0F1fRAL2Pe. Please spread the word!

[Andrew Gordon Wilson @andrewgwils]

LLMs aren't just next-word predictors, they are also compelling zero-shot time series forecasters! Our new NeurIPS paper:
https://t.co/dBNDlrTNNp
w/ @gruver_nate, @m_finzi, @ShikaiQiu
1/7

[Andrew Gordon Wilson @andrewgwils]

We're ecstatic to officially announce our new library, CoLA! CoLA is a framework for large-scale linear algebra in machine learning and beyond, supporting PyTorch and JAX.
repo: https://t.co/UlNPbA8S8U
paper: https://t.co/uDwdNkCf96
w/ amazing @m_finzi, Andres Potap, Geoff Pleiss

[Sanyam Kapoor @psiyumm]

🚨 Come join us at our poster “On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification” at #NeurIPS2022 today (Dec 1) w/ Wesley, @Pavel_Izmailov @andrewgwils 11am-1pm Hall J #715 🚨 https://t.co/aFCtyk8nRl; (Paper: https://t.co/JI5Jshu6Df)

[Pavel Izmailov @Pavel_Izmailov]

We explore how to represent aleatoric (irreducible) uncertainty in Bayesian classification, with profound implications for performance, data augmentation, and cold posteriors in BDL.

https://t.co/Khv3F764By

w/@snymkpr, W. Maddox, @andrewgwils
🧵 1/16

[Sanae Lotfi @LotfiSanae]

I'm so proud that our paper on the marginal likelihood won the Outstanding Paper Award at #ICML2022!!! Congratulations to my amazing co-authors @Pavel_Izmailov, @g_benton_, @micahgoldblum, @andrewgwils 🎉
Talk on Thursday, 2:10 pm, room 310
Poster 828 on Thursday, 6-8 pm, hall E

[Andrew Gordon Wilson @andrewgwils]

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors.
https://t.co/cglYGiLNeM
w/@ziv_ravid, @micahgoldblum, @HosseinSouri8, @snymkpr, @Eiri1114, @ylecun 1/6

[Sanyam Kapoor @psiyumm]

How do we compare between hypotheses that are entirely consistent with the observations? See what @LotfiSanae has to say! 📈

[MoroccoAI @MoroccoAI]

Our next #MoroccoAI webinar will be taking place this Wednesday, the 27th of April! A webinar on 'The Promises and Pitfalls of the marginal likelihood', with Sanae LOTFI.
Please take a minute to RSVP to receive event Zoom link,
https://t.co/hKLcdTTR8d...

#MoroccoAI #AI #morocco

[Polina Kirichenko @polkirichenko]

Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations. ERM learns multiple features that can be reweighted for SOTA on spurious correlations, reducing texture bias on ImageNet, & more!

w/ @Pavel_Izmailov and @andrewgwils
https://t.co/Z4oWb9HH71

1/11

[Mukund Sudarshan @SudarshanMukund]

New ICLR 2022 paper w/ @neiljethani @ianccovert @suinleelab and Rajesh Ranganath! Our ML interpretability method, FastSHAP, significantly speeds up Shapley value estimation by amortizing SHAP/KernelSHAP computations across a training dataset. [📜:https://t.co/IXFiYrKFES]

[Pavel Izmailov @Pavel_Izmailov]

We explore how to represent aleatoric (irreducible) uncertainty in Bayesian classification, with profound implications for performance, data augmentation, and cold posteriors in BDL.

https://t.co/Khv3F764By

w/@snymkpr, W. Maddox, @andrewgwils
🧵 1/16

[Nate Gruver @gruver_nate]

Contrary to expectations, energy conservation and symplecticity are not primarily responsible for the good performance of Hamiltonian neural networks! Our #ICLR2022 paper: https://t.co/pKRTuHxSMK
with @m_finzi, @samscub, and @andrewgwils. 1/7

[Pavel Izmailov @Pavel_Izmailov]

Very excited to give a talk at AABI tomorrow (Feb 1st) at 5PM GMT / 12PM ET!

I will be talking about our recent work on HMC for Bayesian neural networks, cold posteriors, priors, approximate inference and BNNs under distribution shift. Please join!

[Sanyam Kapoor @psiyumm]

@Tkaraletsos Congratulations, Theo!

[Sanyam Kapoor @psiyumm]

🤨#DontLookUp #AcademicTwitter

[Brian Skinner @gravity_levity]

1/2
A Russian mathematician is hired by a math department in the US, and is assigned to teach Calculus 1. On the day before her first lecture, she asks a colleague: "what am I supposed to teach in this class?"

The colleague says, "well, it's standard first-semester calculus...

[Andrew Gordon Wilson @andrewgwils]

I heard a rumour there is this amazing Approximate Inference in Bayesian Deep Learning competition at #NeurIPS2021 tomorrow, starting at 1 pm ET. From what I understand, the winners will be revealing their solutions, and the link to join is https://t.co/dOviUr9Izo. 🤫