1) des gens y travaillent

2) tout a fait d'accord ! Je ne justifiais pas la tâche kafkaïenne. Mon approche est plus de chercher un moyen de contourner que de protester, en général

Un des exemples de motivation derrière la recherche académique sur les LLMs je crois : "ça doit être plus facile d'apprendre a des modèles à écrire que de continuer à remplir ces formulaires

Si seulement il y avait une technologie permettant de faire ça automatiquement ;-)

Being a rejected paper seems like a good criteria (possible issues, but very easy to implement)

I'm surprised, there must have been an additional round of changes.

All the emails I saw as an SAC were "help your ACs write new meta-reviews".

I think that they are hard to bootstrap.

While I agree that general chairs, program chairs, local chairs etc do a lot of work (seeing a glimpse of that sometimes myself with ALT/AISTATS), once you start having a bit of money, it can get easier with using conference organising services

How do-able would it be to organize a conference with its deadline a week after NeurIPS, held a week before, that would always take place physically in Europe (but welcome contributions from anywhere)?

I'm very happy that EurIPS is happening, and planning to attend.

But as a NeurIPS SAC I must say that the last definition should not exist - ACs are supposed to change the decisions and update their meta-review themselves.

At #AISTATS2025, I will be giving an "Oral" presentation of our work on "Implicit Diffusion"

arxiv.org/abs/2402.05468

Il y a plus de 200 notes ?

These findings are quite consistent

Our end-to-end method captures a regression and a classification objective, as well as the autoencoder loss.

We see it as "building a bridge" between these different problems.

8/8

This is a simple generalization from previous binning approaches, the main difference being that we learn the encoding.

We compare different training methods, showing up to 25% improvement on the least-squares baseline error for our full end-to-end method, over 8 datasets.

7/8

You can then train a classification model π_θ (green, top) on the encoded targets, with a KL/cross-entropy objective!

At inference time, you use the same decoder μ to perform your prediction!

6/8

First, the architecture - we use a general target encoder Ψ_w (red, bottom) that transforms the target y in a distribution over k classes

e.g. use softmax(dist) to k different centers

The encoder and the associated decoder μ (in blue) can be trained on an autoencoder loss

5/8

In this work, we propose improvements for "regression as classification"

- Soft-binning: encode the target as a probability, not just a one-hot.
- Learnt target encoders: Instead of designing this transformation by hand, learn it from data.
- Train everything jointly!

4/8

The idea is to transform each value of the target into a class one-hot, and to train a classification model to predict the value of the target. (here with y in 2D, with a grid)

It seems strange, but it's been shown to work well in many settings, even for RL applications.

3/8

An intriguing observation:

In many tasks with a continuous target (price, rating, pitch..), instead of training on a regression objective with least-squares [which seems super natural!] - people have been instead training their models using classification!

2/8

Check out our paper, with Lawrence Stewart and @bachfrancis.bsky.social

Link: arxiv.org/abs/2502.02996

1/8