SLO-Guard improves tuning budget consistency for SLO-constrained LLM serving by handling crashes explicitly and using a two-phase feasible-first exploration plus exploitation strategy.
Bayesian Optimization with Unknown Constraints
6 Pith papers cite this work, alongside 289 external citations. Polarity classification is still indexing.
6
Pith papers citing it
289
external citations · Pith
abstract
Recent work on Bayesian optimization has shown its effectiveness in global optimization of difficult black-box objective functions. Many real-world optimization problems of interest also have constraints which are unknown a priori. In this paper, we study Bayesian optimization for constrained problems in the general case that noise may be present in the constraint functions, and the objective and constraints may be evaluated independently. We provide motivating practical examples, and present a general framework to solve such problems. We demonstrate the effectiveness of our approach on optimizing the performance of online latent Dirichlet allocation subject to topic sparsity constraints, tuning a neural network given test-time memory constraints, and optimizing Hamiltonian Monte Carlo to achieve maximal effectiveness in a fixed time, subject to passing standard convergence diagnostics.
representative citing papers
Safe contextual Bayesian optimization tunes real-world PID controllers for room temperature, achieving 32% cost savings with explicit safety constraints.
TRUST searches for minimal input changes that achieve a user-defined confidence target in PTM models, claiming perfect robustness and low cost on benchmarks versus standard boundary-crossing methods.
SLO-Guard, a crash-aware two-phase autotuner for vLLM serving, achieves no best-latency improvement over random search but demonstrates more consistent budget allocation across 150 trials on Qwen2-1.5B/A100.
Compressing thousands of constraints into a low-dimensional latent space lets Bayesian optimization solve a 108D aeroelastic-tailoring problem with 1,786 black-box constraints, at the cost of slightly worse solution quality on a benchmark.
citing papers explorer
-
SLO-Guard: Crash-Aware, Budget-Consistent Autotuning for SLO-Constrained LLM Serving
SLO-Guard improves tuning budget consistency for SLO-constrained LLM serving by handling crashes explicitly and using a two-phase feasible-first exploration plus exploitation strategy.
-
Safe Contextual Bayesian Optimization for Sustainable Room Temperature PID Control Tuning
Safe contextual Bayesian optimization tunes real-world PID controllers for room temperature, achieving 32% cost savings with explicit safety constraints.
-
Target-confidence Recourse Using tSeTlin machines: TRUST
TRUST searches for minimal input changes that achieve a user-defined confidence target in PTM models, claiming perfect robustness and low cost on benchmarks versus standard boundary-crossing methods.
-
Copy First, Translate Later: Interpreting Translation Dynamics in Multilingual Pretraining
SLO-Guard, a crash-aware two-phase autotuner for vLLM serving, achieves no best-latency improvement over random search but demonstrates more consistent budget allocation across 150 trials on Qwen2-1.5B/A100.
-
High-Dimensional Bayesian Optimisation with Large-Scale Constraints via Latent Space Gaussian Processes
Compressing thousands of constraints into a low-dimensional latent space lets Bayesian optimization solve a 108D aeroelastic-tailoring problem with 1,786 black-box constraints, at the cost of slightly worse solution quality on a benchmark.
- A Human-in-the-Loop Bayesian Optimization Framework for Constraint-Aware Bioprocess Development