We're so excited to be part of this conversation and to have our work highlighted at #NeurIPS22.
We look forward to seeing how continuing collaborations create positive change! #MozFest #TAIWG
Thank you for your great work, @jen_gineered! ⭐️https://twitter.com/jen_gineered/status/1599093957224374272
Original tweet : https://twitter.com/mozillafestival/status/1622915177514426368
A paper at #NeurIPS22
Random Rank: The One and Only Strategyproof and Proportionally Fair Randomized Facility Location Mechanism
https://bytez.com/read/neurips/53479 #NeurIPS2022 #bytez #friendly-papers via @[email protected]
TLDR; Proportionality is an attractive fairness concept that has been applied to a range of problems including the facility location problem. In our work, we propose a concept called Strong Proportionality, which ensures that when there are two groups of agents at different locations, both groups incur the same total cost. We show that there is no deterministic strategyproof mechanism satisfying the property.
Hello Mastodon world! New to this, still learning & hopeful for a kind platform.
As a first post, a late announcement of my #NeurIPS22 work 📢 (still available online if you want to check it out):
- Talk @ attention workshop, org:
@Neurograce @AkankshaSaran et al
- Keynote @ memory workshop, org:
@alex_ander @kennethanorman et al
- 2 panels
- 3 papers at the main conf & workshops
Not sick but still recovering my energy! Send Qs if you came across any of the work and had questions :)
celebrating along with everyone else that we have finally come up with a fantastic #bullshit generator that can help harried students and professors everywhere answer their bullshit exam questions, author their bullshit papers and write their bullshit funding proposals
Given the enormous attention people have been given to #ChatGPT in the last few days, it's fun to read the lukewarm reception of the technical innovations and data collection for the #InstructGPT paper it is based on.
(Although it did still get a solid accept for #Neurips22, of course)
Probabilistic user modeling is essential for building machine learning systems in the ubiquitous cases with humans in the loop. However, modern advanced user models, often designed as cognitive behavior simulators, are incompatible with modern machine learning pipelines and computationally prohibitive for most practical applications. We address this problem by introducing widely-applicable differentiable surrogates for bypassing this computational bottleneck; the surrogates enable computationally efficient inference with modern cognitive models. We show experimentally that modeling capabilities comparable to the only available solution, existing likelihood-free inference methods, are achievable with a computational cost suitable for online applications. Finally, we demonstrate how AI-assistants can now use cognitive models for online interaction in a menu-search task, which has so far required hours of computation during interaction.
Recently, research has increasingly focused on developing efficient neural network architectures. In this work, we explore logic gate networks for machine learning tasks by learning combinations of logic gates. These networks comprise logic gates such as "AND" and "XOR", which allow for very fast execution. The difficulty in learning logic gate networks is that they are conventionally non-differentiable and therefore do not allow training with gradient descent. Thus, to allow for effective training, we propose differentiable logic gate networks, an architecture that combines real-valued logics and a continuously parameterized relaxation of the network. The resulting discretized logic gate networks achieve fast inference speeds, e.g., beyond a million images of MNIST per second on a single CPU core.
Mozilla News & Updates
Toby Walsh
Ida Momennejad
dave's thought experiment
Jelle Zuidema
Jane Adams
Samuel Kaski
Alan Wolfe 👽🐺🎃