Robuta

https://openreview.net/forum?id=1piyfD_ictW On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data | OpenReview It has been empirically observed that training large models with weighted cross-entropy (CE) beyond the zero-training-error regime is not a satisfactory remedy... https://openreview.net/forum?id=0ksNeD1SJT Scaling Exponents Across Parameterizations and Optimizers | OpenReview Robust and effective scaling of models from small to large width typically requires the precise adjustment of many algorithmic and architectural details, such... scalingexponentsacrossparameterizationsoptimizers https://deepai.org/publication/training-integrable-parameterizations-of-deep-neural-networks-in-the-infinite-width-limit Training Integrable Parameterizations of Deep Neural Networks in the Infinite-Width Limit | DeepAI Oct 29, 2021 - 10/29/21 - To theoretically understand the behavior of trained deep neural networks, it is necessary to study the dynamics induced by gradien... deep neural networks https://www.frontiersin.org/journals/physics/articles/10.3389/fphy.2023.1127345/full Frontiers | Parameterizations of immiscible two-phase flow in porous media A fundamental variable characterizing immiscible two-phase flow in porous media is the wetting saturation, which is the ratio between the pore volume fille... two phase flowfrontiersparameterizationsimmiscibleporous https://www.mathworks.com/help/slcontrol/ug/sltuner.showtunable.html showTunable - Show value of parameterizations of tunable blocks of slTuner interface - MATLAB This MATLAB function displays the values of the parametric models associated with each tunable block in the slTuner interface, st. showvalueparameterizationsblocksinterface https://www.pnnl.gov/publications/regional-scale-modeling-parameterizations-secondary-organic-aerosol-formation-isoprene Regional-scale modeling parameterizations for secondary organic aerosol formation from isoprene... secondary organic aerosolscale modelingregionalparameterizations https://www.metoffice.gov.uk/research/weather/atmospheric-dispersion/dispersion-processes Dispersion processes and parameterizations - Met Office Researching turbulent dispersion and improving its representation in the Met Office's atmospheric dispersion model. dispersionprocessesparameterizationsoffice https://arxiv.org/abs/0909.5674 [0909.5674] A model problem for conformal parameterizations of the Einstein constraint equations Abstract page for arXiv paper 0909.5674: A model problem for conformal parameterizations of the Einstein constraint equations https://arxiv.org/abs/1310.4915v1 [1310.4915v1] Fitting ideals and multiple-points of surface parameterizations Abstract page for arXiv paper 1310.4915v1: Fitting ideals and multiple-points of surface parameterizations 1310fittingidealsmultiplepoints https://www.southampton.ac.uk/courses/2029-30/modules/feeg6009 Design Search and Optimisation (DSO) - Principles, Methods, Parameterizations and Case Studies |... This module introduces students to formal design search and optimization (DSO) approaches using a mixture of lectures covering theory and practice and a series... design searchoptimisationdsoprinciplesmethods https://www.southampton.ac.uk/courses/2025-26/modules/feeg6009 Design Search and Optimisation (DSO) - Principles, Methods, Parameterizations and Case Studies |... This module introduces students to formal design search and optimization (DSO) approaches using a mixture of lectures covering theory and practice and a series... design searchoptimisationdsoprinciplesmethods https://www.southampton.ac.uk/courses/2028-29/modules/feeg6009 Design Search and Optimisation (DSO) - Principles, Methods, Parameterizations and Case Studies |... This module introduces students to formal design search and optimization (DSO) approaches using a mixture of lectures covering theory and practice and a series... design searchoptimisationdsoprinciplesmethods https://openreview.net/forum?id=h15RyEj151 Provable Benefits of Complex Parameterizations for Structured State Space Models | OpenReview Structured state space models (SSMs), the core engine behind prominent neural networks such as S4 and Mamba, are linear dynamical systems adhering to a... state space modelsbenefits ofprovablecomplexparameterizations https://deepai.org/publication/alternative-function-approximation-parameterizations-for-solving-games-an-analysis-of-f-regression-counterfactual-regret-minimization Alternative Function Approximation Parameterizations for Solving Games: An Analysis of f-Regression... Dec 6, 2019 - 12/06/19 - Function approximation is a powerful approach for structuring large decision problems that has facilitated great achievements in t... function approximation