←
Robert A. Vandermeulen271 posts
Robert A. Vandermeulen avatar

Robert A. Vandermeulen

@robvdm

Machine Learning and Nonparametric Statistics Researcher

◷ Joined December 2018▧ 9 Photos and videos
Robert A. Vandermeulen avatar
Robert A. Vandermeulen@robvdm·11 Oct 2024

NeurIPS preprint: arxiv.org/abs/2410.07685 Standard models for spatial, sequential, hierarchal, etc data result in drastically reduced effective dimension for density estimation. This effective dimension is orthogonal to other approaches such as sparsity or manifold hypothesis.

Robert A. Vandermeulen avatar
Robert A. Vandermeulen@robvdm·30 Apr 2024

Just noticed that Tsybakov (author of one of my favorite textbooks: Intro. to Nonparametric Estimation) wrote a nice extension of my 2021 NeurIPS paper "Beyond Smoothness: Incorporating Low-Rank Analysis into Nonparametric Density Estimation." Exciting! hal.science/hal-04557030/

Lukas Muttenthaler avatar
⟳ Robert A. Vandermeulen retweeted
Lukas Muttenthaler@lukas_mut·16 Jan 2024

OKO got accepted to #ICLR2024🎉🥳 OKO is very simple to use: Just change your sampling from single data point sampling to set sampling and compute cross-entropy for the sum of set data point logits rather than for single data point logits. You will get much better calibration! 🔥

🚨 Preprint alert🚨 Are you worried about miscalibration of your model outputs but tired of post-hoc temperature scaling and think label smoothing is a hack? Then just train with OKO - a principled set learning approach for better model calibration! (1/5) arxiv.org/abs/2307.02245

Lukas Muttenthaler avatar
⟳ Robert A. Vandermeulen retweeted
Lukas Muttenthaler@lukas_mut·6 Jan 2024

🔥The CfP for Re-Align is up 🔥 If you are broadly interested in the alignment of two or more representation spaces, consider submitting to our workshop at #ICLR2024 and join us in beautiful Vienna!

🚨Call for Papers🚨 The Re-Align Workshop is coming to #ICLR2024 Our CfP is finally up! Come share your representational alignment work at our interdisciplinary workshop at @iclr_conf: representational-alignment.g… 1/4

Andrew Lampinen avatar
⟳ Robert A. Vandermeulen retweeted
Andrew Lampinen@AndrewLampinen·8 Dec 2023

At the poster for @lukas_mut's paper "Improving neural network representations using human similarity judgments" x.com/AndrewLampinen/status/… Wed 13 Dec 10:45 a.m. CST — 12:45 p.m. CST Great Hall & Hall B1+B2 (level 1) #300 nips.cc/virtual/2023/poster/…

What aspects of human conceptual knowledge do machine learning objectives fail to adequately capture? Could we use small datasets of human similarity judgements to improve model representations and get better downstream performance? @lukas_mut's cool new work has the answers!

Robert A. Vandermeulen avatar
Robert A. Vandermeulen@robvdm·7 Dec 2023

It seems like all math tests for LLMs involve just the direct application of various rules, like a bunch of trig or calc rules, to solve the problem. How about getting a LLM to prove the intermediate value theorem or some other proof that requires a clever construction?

Robert A. Vandermeulen avatar
Robert A. Vandermeulen@robvdm·20 Nov 2023

Despite Germans constantly warning me not to, I sit on cold rocks all the time. I guess we Americans just have more robust kidneys.