Pinned Tweet
Denied parole by an ML model? The next best model might have decided otherwise
In our #ICML20 paper w @berkustun @FlavioCalmon, we study the ability for an ML problem to admit competing models with conflicting predictions, which we call "predictive multiplicity"
THREAD ⬇️
Charlie Marx retweeted
I want to offer some unsolicited advice to computer vision researchers jumping into robotics. Don't focus too much on VLMs, VLAs etc. That's fine, but the real action is at the sensorimotor level. Most of the open problems in robotics are in manipulation, which is about hand-object interaction, and contacts and forces are central. Proprioception and tactile sensing are as important as vision. Don't get seduced by cherry-picked demos. You can't do robotics without doing robotics.
Charlie Marx retweeted
I think it’s pretty clear that simulation is the next frontier for AI.
The most impressive feats of AI to date are when we have a clear environment + reward, whether it be beating Le Sedol at Go, winning an IMO gold medal, or writing entire apps from scratch. In these cases, the RL algorithm can try different actions, and observe the well-defined consequences in the safety of a docker container.
But what about messy real-world situations involving people? The rewards are unclear, the stakes are high, and you can’t experiment in the real world. But these situations are precisely where the next big opportunity in AI is. To crack this, we need to *simulate* society (“put society into a docker container”). Concretely, this means building a model that can predict what will happen in any given situation (real or hypothetical). If we can do this, we are only limited by our imagination: predict the future, optimize for better outcomes, answer hypothetical (“what if”) questions. Ultimately, this goes beyond making better decisions, but it’s about giving us a better understanding of ourselves and the world.
Simulation is the whole enchilada. And this is exactly the research that @simile_ai is working on. Read more here:
simile.ai/blog/simulation-ne…
Charlie Marx retweeted
Tired of chasing references across dozens of papers? This monograph distills it all: the principles, intuition, and math behind diffusion models. Thrilled to share!
Tired to go back to the original papers again and again? Our monograph: a systematic and fundamental recipe you can rely on!
📘 We’re excited to release 《The Principles of Diffusion Models》— with @DrYangSong, @gimdong58085414, @mittu1204, and @StefanoErmon.
It traces the core ideas that shaped diffusion modeling and explains how today’s models work, why they work, and where they’re heading.
🧵You’ll find the link and a few highlights in the thread.
We’d love to hear your thoughts and join some discussions!
⚡ Stay tuned for our markdown version, where you can drop your comments!
Charlie Marx retweeted
I have been talking for years in multiple LinkedIn about significant benefits of calibration. It is interesting to see a new paper “Online Calibrated and Conformal Prediction Improves Bayesian Optimization” from Cornell University and Stanford University by @ShachiDeshpande, @CharlieTMarx and @volokuleshov looking at calibration in the Bayesian optimisation domain.
Very interesting results:
1) same as in classifier calibration relying on unrealistic assumptions such as normality can result in inaccurate and overconfident probabilistic models which slows down optimisation and may result in incorrect local optima. The paper provides formal analysis on the benefits of calibration in optimisation setting.
2) conformal prediction based method that can be added to any Bayesian optimisation technique to improve optimisation via faster quality convergence.
These findings are in line with papers I have shared previously, see Amazon Science paper “Optimizing Hyperparameters with Conformal Quantile Regression”
Conformal prediction can significantly improve optimisation methods and is an interesting research domain.
#conformalprediction #optimisation
Charlie Marx retweeted
📢New research on mechanistic architecture design and scaling laws.
- We perform the largest scaling laws analysis (500+ models, up to 7B) of beyond Transformer architectures to date
- For the first time, we show that architecture performance on a set of isolated token manipulation tasks is correlated with metrics of interest at scale, such as compute-optimal loss. Say hello to fast architecture improvement!
- Striped architectures consistently outperform homogeneous architectures, as they benefit from specialization of each layer type to particular subtasks
An avalanche of other findings in the paper:
📝Paper: arxiv.org/abs/2403.17844
🖥️Repo: github.com/athms/mad-lab
Charlie Marx retweeted
Announcing Score Entropy Discrete Diffusion (SEDD) w/ @chenlin_meng @StefanoErmon.
SEDD challenges the autoregressive language paradigm, beating GPT-2 on perplexity and quality!
Arxiv: arxiv.org/abs/2310.16834
Code: github.com/louaaron/Score-En…
Blog: aaronlou.com/blog/discrete-d…
🧵1/n
Charlie Marx retweeted
Personalized models should let users consent to the use of their personal information!
In our latest, we describe how to build models that let users consent to the use of group attributes like sex, age, race, HIV status
Spotlight Poster @NeurIPSConf: Tues 10:45-12:45 PM
Link: nips.cc/virtual/2023/poster/…
Thread 👇
Models are trained on costly data and require this data at prediction time. We should be able to opt-out and understand the gains of opting in!
In our latest w @nagpalchirag @kat_heller @berkustun we introduce models that give users this informed consent
#NeurIPS2023 Spotlight
Charlie Marx retweeted
📢 Diffusion models (DM) generate samples from noise distribution, but for tasks such as image-to-image translation, one side is no longer noise. We present Denoising Diffusion Bridge Models, a simple and scalable extension to DMs suitable for distribution translation problems.
Charlie Marx retweeted
A founder of FAT/ML, Sorelle Friedler (@kdphd) led key OSTP efforts that placed equity, rights, and innovation TOGETHER at the center of tech policy, and illuminated the potential of automated science. Thank you for your incredible service! haverford.edu/college-commun… #AIBillofRights
Charlie Marx retweeted
Thrilled to share that our paper "Comparing Distributions by Measuring Differences that Affect Decision Making" wins #ICLR2022 Outstanding Paper Award🎉blog.iclr.cc/2022/04/20/anno…
Congratulations to my awesome students @shengjia_zhao @a7b2_3 @electronickale Aidan @baaadas👏
Charlie Marx retweeted
This caught my attention, as someone who is interested in decision theory, online learning, and statistical learning.
arxiv.org/abs/2112.13487
Charlie Marx retweeted
The secret heart of academia is... Wikipedia.
In an experiment, this paper found that a single quality Wikipedia article written by chemistry experts influenced the content of 250 published peer-reviewed academic papers! Articles referenced in Wikipedia also become more cited.
Charlie Marx retweeted
It's time for a transition.
1. Moving to @WHOSTP to work with @AlondraNelson46 on bias/fairness.
2. Moving to @BrownUniversity @BrownCSDept @Brown_DSI to work with @senykam on a new center on computing for the people.
14.5 years @UtahSoC - wow!
blog.geomblog.org/2021/05/tr…
We also found this phenomenon interesting!
Would be curious to hear what others see as the implications of these degrees of freedom in human-centric tasks.
Charlie Marx retweeted
Most people in Colorado jails are not convicted of a crime They are poor people who cannot afford their pretrial money bond. Going to jail destabilizes their lives, and the lives of their families, even further.
We must #PassSB21062.
Charlie Marx retweeted
Researchers working in fairness: What are some works that show the usefulness/limitations of Mutual Information(MI) based fairness constraints over others or vice-versa? (1/n)
We'll be @ ICML tomorrow 7/15
11am ET / 5 PM CET
10pm ET/ 7 PM PST
Here's the link:
bit.ly/2OpJvgm