SearcharxivSearch

arXiv subjects

Luis Duque

Publications and source records attributed to Luis Duque.

4 recordsLinked to original sources

LO-FAR: A Cost-Aware Local Filter for Sparse Feature Ranking in Industrial Ad Recommendation

Industrial ad recommendation models rely heavily on sparse, high-cardinality ID-list features that encode user histories and contextual identifiers. Each is backed by a dedicated embedding table, so these features dominate storage, training, and serving cost and must be revisited as traffic and downstream models evolve. Therefore, sparse feature ranking is not just an offline modeling problem but also a recurrent systems decision limited by compute budgets and iteration cadence. We present Localized Feature Ranking (LO-FAR), a CPU-only, model-agnostic workflow that ranks each candidate feature from its stand-alone held-out predictive signal using lightweight local estimators rather than the GPU-bound retraining loops of permutation- and stochastic-gate-based methods. On a production dataset of more than one million logged interactions and 475 sparse ID-list features, LO-FAR completes ranking in approximately two CPU-hours and preserves downstream Normalized Entropy gains on CTR and CVR tasks that are competitive with shuffle-based importance, Binary Stochastic Neurons, and a coverage-based heuristic across budgets of 100--400 retained features. The contribution is a deployable workflow showing that, when cost and turnaround constraints are binding, a simple local filter can be a practical production choice over heavier interaction-aware alternatives.

cs.IR

Study of Mass Transport in the Anode of a Proton Exchange Membrane Fuel Cell with a New Hydrogen Flow-Rate Modulation Technique

Hydrogen transport in the anode of a proton-exchange membrane fuel cell (PEMFC) has been studied with a modulation technique relating the hydrogen flow-rate $(\tilde{Q}_{H2})$ and the faradaic current $(\tilde{I})$, called $\textit{Current-modulated Hydrogen flow-rate Spectroscopy}$ (CH2S). A simple analytical expression for the transfer function, $H(j{\omega})=n \, F \, \tilde{Q}_{H2} \mathbin{/} \tilde{I}$, is provided, showing a skewed semicircle in Nyquist representation ($-H^{''}$ vs. $H^{'}$), extending from $H^{'}=0\:$ to $H^{'}=1$, and with the maximum frequency at ${\omega}_{max}=2.33\,(D_{H2}\mathbin{/}{L_{i}}^{2})$, where $D_{H2}$ is the effective hydrogen diffusivity and $L_i$ the thickness of the anode gas diffusion layer (GDL). The expression for CH2S is also calculated with an existing reversible chemical reaction in the GDL. Experimental results under different operation conditions show two transport processes limiting the anode reaction, one attributed to molecular diffusion through the partially saturated GDL, and the other to the microporous layer (MPL), or its interfaces with GDL or with the catalyst layer (CL). CH2S provides the hydrogen diffusivities $(D_{H2,i})$ associated to each process under the different conditions. Current density decreases slightly the diffusivity of the GDL, while it becomes activated in the MPL; using two GDLs in the anode improves both GDL and MPL diffusivities; humidification decreases the diffusivity in both, GDL and MPL; finally, a superhydrophobic anodic CL prepared by electrospray improves hydrogen diffusivity in GDL and MPL.

physics.chem-ph

The double obstacle problem on non divergence form

We study the regularity of the solution of the double obstacle problem form for fully non linear parabolic and elliptic operators. We show that when the obstacles are sufficiently regular the solution is $C^{1,\alpha}$ in the interior for both the parabolic and the elliptic cases.

math.AP

The two membranes problem for fully nonlinear operators

We study the two membranes problem for two different fully nonlinear operators. We give a viscosity formulation for the problem and prove existence of solutions. Then we prove a general regularity result and the optimal $C^{1,1}$ regularity when the operators are the Pucci extremal operators. We also give an example that shows that no regularity for the free boundary is to be expected to hold in general.

math.AP