Integrating Combinatorial Solvers and Neural Models

Add to your list(s) Download to your calendar using vCal

• Pasquale Minervi, University of Edinburgh
• Friday 23 February 2024, 12:00-13:00
• https://cam-ac-uk.zoom.us/j/86071371348?pwd=OVlqdDhZNHlGbzV5RUZrSzM1cUlhUT09.

If you have a question about this talk, please contact Richard Diehl Martinez.

Neural models—including language models such as ChatGPT—can exhibit remarkable abilities; paradoxically, they also struggle with algorithmic tasks where much simpler models excel. To solve these issues, we propose Implicit Maximum Likelihood Estimation (IMLE), a framework for end-to-end learning of models combining algorithmic combinatorial solvers and differentiable neural components, which allows us to incorporate planning and reasoning algorithms in neural architectures by just adding a simple decorator [1, 2].

[1] Implicit MLE : Backpropagating Through Discrete Exponential Family Distributions. https://arxiv.org/abs/2106.01798, NeurIPS 2021 [2] Adaptive Perturbation-Based Gradient Estimation for Discrete Latent Variable Models. https://arxiv.org/abs/2209.04862, AAAI 2023

Join Zoom Meeting

https://cam-ac-uk.zoom.us/j/86071371348?pwd=OVlqdDhZNHlGbzV5RUZrSzM1cUlhUT09

Meeting ID: 860 7137 1348

Passcode: 387918

This talk is part of the NLIP Seminar Series series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge Centre for Data-Driven Discovery (C2D3)
• Cambridge Forum of Science and Humanities
• Cambridge Language Sciences
• Cambridge talks
• Chris Davis' list
• Department of Computer Science and Technology talks and seminars
• Graduate-Seminars
• Guy Emerson's list
• Interested Talks
• Language Sciences for Graduate Students
• NLIP Seminar Series
• PMRFPS's
• Simon Baker's List
• Trust & Technology Initiative - interesting events
• bld31
• https://cam-ac-uk.zoom.us/j/86071371348?pwd=OVlqdDhZNHlGbzV5RUZrSzM1cUlhUT09
• ndk22's list
• ob366-ai4er
• rp587

Note that ex-directory lists are not shown.