Zobrazeno 1 - 10
of 389
pro vyhledávání: '"Mandel, Louis"'
Large language models (LLMs) have taken the world by storm by making many previously difficult uses of AI feasible. LLMs are controlled via highly expressive textual prompts and return textual answers. Unfortunately, this unstructured text as input a
Externí odkaz:
http://arxiv.org/abs/2410.19135
Advanced probabilistic programming languages (PPLs) use hybrid inference systems to combine symbolic exact inference and Monte Carlo methods to improve inference performance. These systems use heuristics to partition random variables within the progr
Externí odkaz:
http://arxiv.org/abs/2408.11283
Autor:
Sahoo, Priyam, Pujar, Saurabh, Nalawade, Ganesh, Gebhardt, Richard, Mandel, Louis, Buratti, Luca
The availability of Large Language Models (LLMs) which can generate code, has made it possible to create tools that improve developer productivity. Integrated development environments or IDEs which developers use to write software are often used as a
Externí odkaz:
http://arxiv.org/abs/2402.17442
Large language models (LLMs) have become remarkably good at improving developer productivity for high-resource programming languages. These models use two kinds of data: large amounts of unlabeled code samples for pre-training and relatively smaller
Externí odkaz:
http://arxiv.org/abs/2310.16937
Synchronous languages are now a standard industry tool for critical embedded systems. Designers write high-level specifications by composing streams of values using block diagrams. These languages have been extended with Bayesian reasoning to program
Externí odkaz:
http://arxiv.org/abs/2308.01676
In this extended abstract, we discuss the opportunity to formally verify that inference systems for probabilistic programming guarantee good performance. In particular, we focus on hybrid inference systems that combine exact and approximate inference
Externí odkaz:
http://arxiv.org/abs/2307.07355
Efficient inference is often possible in a streaming context using Rao-Blackwellized particle filters (RBPFs), which exactly solve inference problems when possible and fall back on sampling approximations when necessary. While RBPFs can be implemente
Externí odkaz:
http://arxiv.org/abs/2209.07490
Autor:
Benzaken, Véronique, Contejean, Évelyne, Hachmaoui, Mohammed Houssem, Keller, Chantal, Mandel, Louis, Shinnar, Avraham, Siméon, Jérôme
SQL is by far the most widely used and implemented query language. Yet, on some key features, such as correlated queries and NULL value semantics, many implementations diverge or contain bugs. We leverage recent advances in the formalization of SQL a
Externí odkaz:
http://arxiv.org/abs/2203.08941
Autor:
Baudart, Guillaume, Mandel, Louis
Stan is a very popular probabilistic language with a state-of-the-art HMC sampler but it only offers a limited choice of algorithms for black-box variational inference. In this paper, we show that using our recently proposed compiler from Stan to Pyr
Externí odkaz:
http://arxiv.org/abs/2110.11790
Publikováno v:
Proc. ACM Program. Lang. 5, OOPSLA, Article 115 (October 2021)
Probabilistic programming languages aid developers performing Bayesian inference. These languages provide programming constructs and tools for probabilistic modeling and automated inference. Prior work introduced a probabilistic programming language,
Externí odkaz:
http://arxiv.org/abs/2109.12473