Zobrazeno 1 - 10
of 16 143
pro vyhledávání: '"Niles A"'
Autor:
Ferdaus, Md Meftahul, Abdelguerfi, Mahdi, Ioup, Elias, Dobson, David, Niles, Kendall N., Pathak, Ken, Sloan, Steven
We introduce KANICE (Kolmogorov-Arnold Networks with Interactive Convolutional Elements), a novel neural architecture that combines Convolutional Neural Networks (CNNs) with Kolmogorov-Arnold Network (KAN) principles. KANICE integrates Interactive Co
Externí odkaz:
http://arxiv.org/abs/2410.17172
Mixed multinomial logits are discrete mixtures introduced several decades ago to model the probability of choosing an attribute from $p$ possible candidates, in heterogeneous populations. The model has recently attracted attention in the AI literatur
Externí odkaz:
http://arxiv.org/abs/2409.09903
We propose a procedure for estimating the Schr\"odinger bridge between two probability distributions. Unlike existing approaches, our method does not require iteratively simulating forward and backward diffusions or training neural networks to fit un
Externí odkaz:
http://arxiv.org/abs/2408.11686
The unadjusted Langevin algorithm is commonly used to sample probability distributions in extremely high-dimensional settings. However, existing analyses of the algorithm for strongly log-concave distributions suggest that, as the dimension $d$ of th
Externí odkaz:
http://arxiv.org/abs/2408.13115
Autor:
Alshawi, Rasha, Ferdaus, Md Meftahul, Abdelguerfi, Mahdi, Niles, Kendall, Pathak, Ken, Sloan, Steve
Imbalanced datasets are a significant challenge in real-world scenarios. They lead to models that underperform on underrepresented classes, which is a critical issue in infrastructure inspection. This paper introduces the Enhanced Feature Pyramid Net
Externí odkaz:
http://arxiv.org/abs/2408.10181
Autor:
Han, Yanjun, Niles-Weed, Jonathan
We prove bounds on statistical distances between high-dimensional exchangeable mixture distributions (which we call permutation mixtures) and their i.i.d. counterparts. Our results are based on a novel method for controlling $\chi^2$ divergences betw
Externí odkaz:
http://arxiv.org/abs/2408.09341
Autor:
Alshawi, Rasha, Ferdaus, Md Meftahul, Hoque, Md Tamjidul, Niles, Kendall, Pathak, Ken, Sloan, Steve, Abdelguerfi, Mahdi
This paper introduces Semantic Haar-Adaptive Refined Pyramid Network (SHARP-Net), a novel architecture for semantic segmentation. SHARP-Net integrates a bottom-up pathway featuring Inception-like blocks with varying filter sizes (3x3$ and 5x5), paral
Externí odkaz:
http://arxiv.org/abs/2408.08879
We present an introduction to the field of statistical optimal transport, based on lectures given at \'Ecole d'\'Et\'e de Probabilit\'es de Saint-Flour XLIX.
Comment: Lecture Notes for \'Ecole d'\'Et\'e de Probabilit\'es de Saint-Flour XLIX 2019
Comment: Lecture Notes for \'Ecole d'\'Et\'e de Probabilit\'es de Saint-Flour XLIX 2019
Externí odkaz:
http://arxiv.org/abs/2407.18163
Autor:
Kassraie, Parnian, Pooladian, Aram-Alexandre, Klein, Michal, Thornton, James, Niles-Weed, Jonathan, Cuturi, Marco
Optimal transport (OT) has profoundly impacted machine learning by providing theoretical and computational tools to realign datasets. In this context, given two large point clouds of sizes $n$ and $m$ in $\mathbb{R}^d$, entropic OT (EOT) solvers have
Externí odkaz:
http://arxiv.org/abs/2406.05061
Autor:
Ferdaus, Md Meftahul, Abdelguerfi, Mahdi, Ioup, Elias, Niles, Kendall N., Pathak, Ken, Sloan, Steven
The rapid progress in Large Language Models (LLMs) could transform many fields, but their fast development creates significant challenges for oversight, ethical creation, and building user trust. This comprehensive review looks at key trust issues in
Externí odkaz:
http://arxiv.org/abs/2407.13934