Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Ndiaye, Eugene"'
Autor:
Kirchhof, Michael, Thornton, James, Ablin, Pierre, Béthune, Louis, Ndiaye, Eugene, Cuturi, Marco
The increased adoption of diffusion models in text-to-image generation has triggered concerns on their reliability. Such models are now closely scrutinized under the lens of various metrics, notably calibration, fairness, or compute efficiency. We fo
Externí odkaz:
http://arxiv.org/abs/2410.06025
Conformal prediction methodologies have significantly advanced the quantification of uncertainties in predictive models. Yet, the construction of confidence regions for model parameters presents a notable challenge, often necessitating stringent assu
Externí odkaz:
http://arxiv.org/abs/2405.18601
Publikováno v:
International Conference of Learning Representations 2024
Conformal prediction (CP) for regression can be challenging, especially when the output distribution is heteroscedastic, multimodal, or skewed. Some of the issues can be addressed by estimating a distribution over the output, but in reality, such app
Externí odkaz:
http://arxiv.org/abs/2404.08168
Beyond minimizing a single training loss, many deep learning estimation pipelines rely on an auxiliary objective to quantify and encourage desirable properties of the model (e.g. performance on another dataset, robustness, agreement with a prior). Al
Externí odkaz:
http://arxiv.org/abs/2402.02998
We explore a novel methodology for constructing confidence regions for parameters of linear models, using predictions from any arbitrary predictor. Our framework requires minimal assumptions on the noise and can be extended to functions deviating fro
Externí odkaz:
http://arxiv.org/abs/2401.15254
The inability to linearly classify XOR has motivated much of deep learning. We revisit this age-old problem and show that linear classification of XOR is indeed possible. Instead of separating data between halfspaces, we propose a slightly different
Externí odkaz:
http://arxiv.org/abs/2312.01541
Given a sequence of observable variables $\{(x_1, y_1), \ldots, (x_n, y_n)\}$, the conformal prediction method estimates a confidence set for $y_{n+1}$ given $x_{n+1}$ that is valid for any finite sample size by merely assuming that the joint distrib
Externí odkaz:
http://arxiv.org/abs/2307.05109
Autor:
Klein, Michal, Pooladian, Aram-Alexandre, Ablin, Pierre, Ndiaye, Eugène, Niles-Weed, Jonathan, Cuturi, Marco
Given a source and a target probability measure supported on $\mathbb{R}^d$, the Monge problem asks to find the most efficient way to map one distribution to the other. This efficiency is quantified by defining a \textit{cost} function between source
Externí odkaz:
http://arxiv.org/abs/2306.11895
Autor:
Johnstone, Chancellor, Ndiaye, Eugene
It is common in machine learning to estimate a response $y$ given covariate information $x$. However, these predictions alone do not quantify any uncertainty associated with said predictions. One way to overcome this deficiency is with conformal infe
Externí odkaz:
http://arxiv.org/abs/2210.17405
In predictive modeling for high-stake decision-making, predictors must be not only accurate but also reliable. Conformal prediction (CP) is a promising approach for obtaining the confidence of prediction results with fewer theoretical assumptions. To
Externí odkaz:
http://arxiv.org/abs/2205.14317