Zobrazeno 1 - 10
of 178
pro vyhledávání: '"Püschel, Markus"'
Autor:
Chevalley, Mathieu, Sackett-Sanders, Jacob, Roohani, Yusuf, Notin, Pascal, Bakulin, Artemy, Brzezinski, Dariusz, Deng, Kaiwen, Guan, Yuanfang, Hong, Justin, Ibrahim, Michael, Kotlowski, Wojciech, Kowiel, Marcin, Misiakos, Panagiotis, Nazaret, Achille, Püschel, Markus, Wendler, Chris, Mehrjou, Arash, Schwab, Patrick
In drug discovery, mapping interactions between genes within cellular systems is a crucial early step. This helps formulate hypotheses regarding molecular mechanisms that could potentially be targeted by future medicines. The CausalBench Challenge wa
Externí odkaz:
http://arxiv.org/abs/2308.15395
We present ongoing work on a new automatic code generation approach for supporting quantized generative inference on LLMs such as LLaMA or OPT on off-the-shelf CPUs. Our approach is informed by the target architecture and a performance model, includi
Externí odkaz:
http://arxiv.org/abs/2307.03738
Publikováno v:
NeurIPS 2023
We present a novel perspective and algorithm for learning directed acyclic graphs (DAGs) from data generated by a linear structural equation model (SEM). First, we show that a linear SEM can be viewed as a linear transform that, in prior work, comput
Externí odkaz:
http://arxiv.org/abs/2305.15936
M\"obius inversion of functions on partially ordered sets (posets) $\mathcal{P}$ is a classical tool in combinatorics. For finite posets it consists of two, mutually inverse, linear transformations called zeta and M\"obius transform, respectively. In
Externí odkaz:
http://arxiv.org/abs/2211.13706
We present a novel form of Fourier analysis, and associated signal processing concepts, for signals (or data) indexed by edge-weighted directed acyclic graphs (DAGs). This means that our Fourier basis yields an eigendecomposition of a suitable notion
Externí odkaz:
http://arxiv.org/abs/2209.07970
This paper focuses on finite-time in-network computation of linear transforms of distributed graph data. Finite-time transform computation problems are of interest in graph-based computing and signal processing applications in which the objective is
Externí odkaz:
http://arxiv.org/abs/2104.01502
Publikováno v:
Proceedings of the ACM on Programming Languages, Volume 6, Issue POPL, January 2022, Article No.: 43, pp 1-33
Formal verification of neural networks is critical for their safe adoption in real-world applications. However, designing a precise and scalable verifier which can handle different activation functions, realistic network architectures and relevant sp
Externí odkaz:
http://arxiv.org/abs/2103.03638
Publikováno v:
IEEE Transactions on Signal Processing, Vol. 69, pp. 3571-3584, 2021
A lattice is a partially ordered set supporting a meet (or join) operation that returns the largest lower bound (smallest upper bound) of two elements. Just like graphs, lattices are a fundamental structure that occurs across domains including social
Externí odkaz:
http://arxiv.org/abs/2012.04358
Publikováno v:
Proc. AAAI, 2021
Many applications of machine learning on discrete domains, such as learning preference functions in recommender systems or auctions, can be reduced to estimating a set function that is sparse in the Fourier domain. In this work, we present a new fami
Externí odkaz:
http://arxiv.org/abs/2010.00439
Publikováno v:
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence Main Track (2022). Pages 549-556
Recent advances in Fourier analysis have brought new tools to efficiently represent and learn set functions. In this paper, we bring the power of Fourier analysis to the design of combinatorial auctions (CAs). The key idea is to approximate bidders'
Externí odkaz:
http://arxiv.org/abs/2009.10749