DS
David Salinas
cs.LGstat.MLcs.AIcs.CL
On Valency
published · living versionsW_ccx6rfnx·v1 · currentpublished
The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It
with Hannan Mahadik, Jacek Golebiowski, Aaron Klein
1 version
Preprints & journals
36 papers in the corpus · 2017–2026Turnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State Machine2610.07070v1 · Aaron Fainman, Gabriela Kadlecov'a, Maciej Gryka et al.2026 · 0 citationsarXiv
TabPFN-3.5: Technical Report2609.17895v2 · Benjamin Jager, Nick Erickson, L'eo Grinsztajn et al.2026 · 0 citationsarXiv
MultiSynt/MT: Trillion-Token Multi-Parallel Pre-Training Data Translated Across 36 Languages2607.00890v2 · Maximilian Idahl, Jorg Tiedemann, Sampo Pyysalo et al.2026 · 0 citationsarXiv
JudgeArena: A Unified Framework for Reproducible LLM-Judge Evaluation2608.02620v1 · Erlis Lushtaku, Bora Kargi, Ali Elganzory et al.2026 · 0 citationsarXiv
From Uncertain Judgments to Calibrated Rankings: Conformal Elo Estimation for LLM Evaluation2606.13221v3 · Bora Kargi, David Salinas2026 · 0 citationsarXiv
An Open-Source Training Dataset for Foundation Models for Black-box Optimization2605.23417v1 · Aaron Klein, Herilalaina Rakotoarison, Luca Thale-Bombien et al.2026 · 0 citationsarXiv
TabPFN-3: Technical Report2605.13986v2 · L'eo Grinsztajn, Klemens Floge, Oscar Key et al.2026 · 3 citationsarXiv
Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting2603.08707v2 · Azul Garza, Ren'ee Rosillo, Rodrigo Mendoza-Smith et al.2026 · 0 citationsarXiv
Multi-Objective Hierarchical Optimization with Large Language Models2601.13892v1 · Andrej Schwanke, Lyubomir Ivanov, David Salinas et al.2026 · 0 citationsarXiv
MixtureVitae: Open Web-Scale Pretraining Dataset With High Quality Instruction and Reasoning Data Built from Permissive-First Text Sources2509.25531v5 · Huu Nguyen, Victor May, Harsh Raj et al.2025 · 0 citationsarXiv
Open-sci-ref-0.02: open reference baselines for reproducible language model and dataset comparison2509.09009v4 · Marianna Nezhurina, Harsh Raj, Victor May et al.2025 · 0 citationsarXiv
TabArena: A Living Benchmark for Machine Learning on Tabular Data2506.16791v4 · Nick Erickson, Lennart Purucker, Andrej Tschalzev et al.2025 · 12 citationsarXiv
Improving LLM-based Global Optimization with Search Space Partitioning2505.21372v2 · Andrej Schwanke, Lyubomir Ivanov, David Salinas et al.2025 · 0 citationsarXiv
EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Networks2502.06684v4 · Michael Arbel, David Salinas, Frank Hutter2025 · 0 citationsarXiv
Tuning LLM Judge Design Decisions for 1/1000 of the Cost2501.17178v4 · David Salinas, Omar Swelam, Frank Hutter2025 · 0 citationsarXiv
From Tables to Time: Extending TabPFN-v2 to Time Series Forecasting2501.02945v4 · Shi Bin Hoo, Samuel Muller, David Salinas et al.2025 · 6 citationsarXiv
Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models2410.09385v1 · Sathya Kamesh Bhethanabhotla, Omar Swelam, Julien Siems et al.2024 · 2 citationsarXiv
GAMformer: Bridging Tabular Foundation Models and Interpretable Machine Learning2410.04560v2 · Andreas Mueller, Julien Siems, Harsha Nori et al.2024 · 1 citationarXiv
ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning2409.18827v2 · Jannis Becktepe, Julian Dierkes, Carolin Benjamins et al.2024 · 0 citationsJournal of Data-centric Machine Learning Research; 2026
Deep Non-Parametric Time Series Forecaster2312.14657v1 · Syama Sundar Rangapuram, Jan Gasthaus, Lorenzo Stella et al.2023 · 4 citationsarXiv
TabRepo: A Large Scale Repository of Tabular Model Evaluations and its AutoML Applications2311.02971v3 · David Salinas, Nick Erickson2023 · 3 citationsarXiv
Obeying the Order: Introducing Ordered Transfer Hyperparameter Optimisation2306.16916v1 · Sigrid Passano Hellan, Huibin Shen, Francois-Xavier Aubet et al.2023 · 0 citationsarXiv
Optimizing Hyperparameters with Conformal Quantile Regression2305.03623v1 · David Salinas, Jacek Golebiowski, Aaron Klein et al.2023 · 3 citationsarXiv
Criteria for Classifying Forecasting Methods2212.03523v1 · Tim Januschowski, Jan Gasthaus, Yuyang Wang et al.2022 · 210 citationsarXiv
Multi-Objective Model Selection for Time Series Forecasting2202.08485v1 · Oliver Borchert, David Salinas, Valentin Flunkert et al.2022 · 7 citationsarXiv
Meta-Forecasting by combining Global Deep Representations with Local Adaptation2111.03418v2 · Riccardo Grazzi, Valentin Flunkert, David Salinas et al.2021 · 2 citationsarXiv
Multi-objective Asynchronous Successive Halving2106.12639v1 · Robin Schmucker, Michele Donini, Muhammad Bilal Zafar et al.2021 · 6 citationsarXiv
A multi-objective perspective on jointly tuning hardware and hyperparameters2106.05680v1 · David Salinas, Valerio Perrone, Olivier Cruchant et al.2021 · 1 citationarXiv
A resource-efficient method for repeated HPO and NAS problems2103.16111v2 · Giovanni Zappella, David Salinas, C'edric Archambeau2021 · 0 citationsarXiv
The Effectiveness of Discretization in Forecasting: An Empirical Study on Neural Time Series Models2005.10111v1 · Stephan Rabanser, Tim Januschowski, Valentin Flunkert et al.2020 · 18 citationsarXiv
Deep Learning for Time Series Forecasting: Tutorial and Literature Survey2004.10240v2 · Konstantinos Benidis, Syama Sundar Rangapuram, Valentin Flunkert et al.2020 · 380 citationsACM Computing Surveys (2022)
High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes1910.03002v2 · David Salinas, Michael Bohlke-Schneider, Laurent Callot et al.2019 · 105 citationsarXiv
A Quantile-based Approach for Hyperparameter Transfer Learning1909.13595v2 · David Salinas, Huibin Shen, Valerio Perrone2019 · 22 citationsarXiv
GluonTS: Probabilistic Time Series Models in Python1906.05264v2 · Alexander Alexandrov, Konstantinos Benidis, Michael Bohlke-Schneider et al.2019 · 75 citationsarXiv
Approximate Bayesian Inference in Linear State Space Models for Intermittent Demand Forecasting at Scale1709.07638v1 · Matthias Seeger, Syama Rangapuram, Yuyang Wang et al.2017 · 10 citationsarXiv
DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks1704.04110v3 · David Salinas, Valentin Flunkert, Jan Gasthaus2017 · 2,726 citationsarXiv
Career total: 66 works. 36 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.