Zobrazeno 1 - 10
of 5 684
pro vyhledávání: '"Llinares, A."'
Let $\mathfrak{p}_d(q)$ denote the critical exponent of the Riesz projection from $L^q(\mathbb{T}^d)$ to the Hardy space $H^p(\mathbb{T}^d)$, where $\mathbb{T}$ is the unit circle. We present the state-of-the-art on the conjecture that $\mathfrak{p}_
Externí odkaz:
http://arxiv.org/abs/2402.09787
Autor:
Marion, Pierre, Korba, Anna, Bartlett, Peter, Blondel, Mathieu, De Bortoli, Valentin, Doucet, Arnaud, Llinares-López, Felipe, Paquette, Courtney, Berthet, Quentin
We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling processes by optimizing over their parameters. We introduce a general fr
Externí odkaz:
http://arxiv.org/abs/2402.05468
Autor:
Guo, Shangmin, Zhang, Biao, Liu, Tianlin, Liu, Tianqi, Khalman, Misha, Llinares, Felipe, Rame, Alexandre, Mesnard, Thomas, Zhao, Yao, Piot, Bilal, Ferret, Johan, Blondel, Mathieu
Direct alignment from preferences (DAP) methods, such as DPO, have recently emerged as efficient alternatives to reinforcement learning from human feedback (RLHF), that do not require a separate reward model. However, the preference datasets used in
Externí odkaz:
http://arxiv.org/abs/2402.04792
There are several international standards that define the way to evaluate the attenuation capacity of noise reducing devices, by single-number quantities representing airborne sound insulation and insertion loss. These two single-value ratings define
Externí odkaz:
http://arxiv.org/abs/2402.04136
Autor:
Liu, Tianlin, Guo, Shangmin, Bianco, Leonardo, Calandriello, Daniele, Berthet, Quentin, Llinares, Felipe, Hoffmann, Jessica, Dixon, Lucas, Valko, Michal, Blondel, Mathieu
Aligning language models with human preferences is crucial for reducing errors and biases in these models. Alignment techniques, such as reinforcement learning from human feedback (RLHF), are typically cast as optimizing a tradeoff between human pref
Externí odkaz:
http://arxiv.org/abs/2402.02992
Publikováno v:
J. Math. Anal. Appl. 538 (2024), no. 2, Paper no. 128387, 14 pp
We study the convolution of functions of the form \[ f_\alpha (z) := \dfrac{\left( \frac{1 + z}{1 - z} \right)^\alpha - 1}{2 \alpha}, \] which map the open unit disk of the complex plane onto polygons of 2 edges when $\alpha\in(0,1)$. We extend resul
Externí odkaz:
http://arxiv.org/abs/2311.12937
Publikováno v:
Aquaculture Environment Interactions, Vol 16, Pp 213-225 (2024)
Infestations with the ectoparasite salmon louse Lepeophtheirus salmonis are considered one of the main stressors for wild salmonids in farm-intensive areas. In Norway, lice infestations on sea trout Salmo trutta are monitored annually at fixed statio
Externí odkaz:
https://doaj.org/article/22c7924531354caf80797065d471fb65
We characterize the restrictions of B\'ekoll\'e--Bonami weights of bounded hyperbolic oscillation, to subsets of the unit disc, thus proving an analogue of Wolff's restriction theorem for Muckenhoupt weights. Sundberg proved a discrete version of Wol
Externí odkaz:
http://arxiv.org/abs/2308.04859
We show that the Korenblum maximum (domination) principle is valid for weighted Bergman spaces $A^p_w$ with arbitrary (non-negative and integrable) radial weights $w$ in the case $1\le p<\infty$. We also notice that in every weighted Bergman space th
Externí odkaz:
http://arxiv.org/abs/2307.14699
Publikováno v:
37th Conference on Neural Information Processing Systems, Dec 2023, New Orleans, United States
We introduce a differentiable clustering method based on stochastic perturbations of minimum-weight spanning forests. This allows us to include clustering in end-to-end trainable pipelines, with efficient gradients. We show that our method performs w
Externí odkaz:
http://arxiv.org/abs/2305.16358