Fast Rank-1 Lattice Targeted Sampling for Black-box Optimization
10. prosince 2023
Řečníci
Yueming Lyu
Řečník · 0 sledujících
O prezentaci
Black-box optimization has gained great attention for its success in recent applications. However, scaling up to high-dimensional problems with good query efficiency remains challenging. This paper proposes a novel Rank-1 Lattice Targeted Sampling (RLTS) technique to address this issue. Our RLTS benefits from random rank-1 lattice Quasi-Monte Carlo, which enables us to perform fast local exact Gaussian processes (GP) training and inference with O(n log n) complexity w.r.t. n batch samples. Furthermore, we developed a fast coordinate searching method with O(n log n) time complexity for fast targeted sampling. The fast computation enables us to plug our RLTS into the sampling phase of stochastic optimization methods. This improves the query efficiency while scaling up to higher dimensional problems than Bayesian optimization. Moreover, to construct rank-1 lattices efficiently, we proposed a closed-form construction. Extensive experiments on challenging benchmark test functions and black-box prompt fine-tuning for large language models demonstrate the query efficiency of our RLTS technique.Black-box optimization has gained great attention for its success in recent applications. However, scaling up to high-dimensional problems with good query efficiency remains challenging. This paper proposes a novel Rank-1 Lattice Targeted Sampling (RLTS) technique to address this issue. Our RLTS benefits from random rank-1 lattice Quasi-Monte Carlo, which enables us to perform fast local exact Gaussian processes (GP) training and inference with O(n log n) complexity w.r.t. n batch samples. Furth…
Organizátor
NeurIPS 2023
Účet · 623 sledujících
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
TOA: Task-oriented Active VQA
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Fantastic Robustness Measures: The Secrets of Robust Generalization
Zhlédnout později
Hoki Kim, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Mode Connectivity in Auction Design
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Debiasing Conditional Stochastic Optimization
Zhlédnout později
Lie He, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
On the Size and Approximation Error of Distilled Datasets
Zhlédnout později
Alaa Maalouf, …
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %
Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning
Zhlédnout později
Pro uložení prezentace do věčného trezoru hlasovalo 0 diváků, což je 0.0 %