OmniOpt supplies the research community with an operational coordinate system for selecting optimizers under explicit mechanism and objective assumptions, and charts a direction for the future development of the optimizer community.
Abstract
Optimizer selection for large-scale model training has become a system-level design decision constrained jointly by compute, memory, tuning budget, and task diversity, yet the landscape of over one hundred methods remains fragmented. We therefore present OmniOpt, a unified survey and benchmark cookbook of optimizers for the research community. OmniOpt rests on four coupled components. First, we treat every optimizer update as a structured transformation through a five-stage meta-pipeline, and show that most methods engage only one or two of these stages. Second, we use norm-constrained linear minimization oracles (LMOs) to unify different optimizers. Third, these two views ground a dual-dimension taxonomy, one dimension assigning each method to a mechanism family and the other recording the measurable training objectives it aims to improve. Fourth, and at the core of this paper, we instantiate the full taxonomy in a unified cross-domain benchmark spanning representative optimizers, model scales, and training regimes from language model pretraining to image classification, systematically analyzing each method family across multiple effect objectives and laying out their trade-offs. OmniOpt thus supplies the research community with an operational coordinate system for selecting optimizers under explicit mechanism and objective assumptions, and charts a direction for the future development of the optimizer community.
Configuring and tuning modern software is unavoidable, expensive, and error-prone: a single system can expose hundreds of interacting options, and scoring one setting can mean a full build or test run. The standard response is automated optimization, but the number of available optimizers is large and growing. And some of the guidance for selecting among them is misleading: NSGA-II, for example, is widely recommended, yet other algorithms reach the same results using only 1/20th as many evaluations. To help practitioners make better choices about tools to configure their systems, we cluster 20 optimizers, based on six assumptions about the data. Next, we run a tournament across those optimizers, using 106 SE optimization tasks at four labeling budgets (taking 14,000+ CPU hours). We find that no optimizer wins outright. The best one migrates with the budget (from a geometric active learner when labels are scarce to differential evolution when labels are plentiful) so a winner"crowned"at one budget is wrong at another on up to half our tasks. Running such a tournament for every new domain is impractical due to its CPU cost. Fortunately, we find that those 14,000 hours can be replaced by a table lookup over two cheap-to-obtain task attributes (plus the labeling budget). Predictions from this table tie or beat a hindsight oracle on $\approx 75%$ of held-out tasks. To support open science, our tournament and replication package are open-sourced for SBSE researchers and practitioners at https://github.com/KKGanguly/OptimizerTournament.
Kishan Kumar Ganguly, Tim Menzies· arXiv.org· 0 citations
This work proposes an automated framework that generates and refines benchmark suites using large language models (LLMs) and evolutionary search and shows that this combined approach substantially increases discriminability, improving scores from approximately 2.04 to 2.58.
Ananta Shahane, Niki van Stein· GECCO Companion· 0 citations
The design of transformer-based Large Language Models (LLMs) is being radically changed through new architectures that are able to overcome scalability limitations of previous designs, including Mixture-of-Experts (MoE), Multi-Head Latent Attention (MLA), and Multi-Token Prediction (MTP). As an open-weighted model released at the end of 2024, which has both state of the art architectural transparency and production scale efficiency, DeepSeeek-V3 represents the ultimate testing ground for investigating these modern technologies. This paper provides a comprehensive analysis of the architectural structure of DeepSeek-V3 based upon information from the DeepSeek-V3 Technical Report, industry benchmarking data and independent latency testing, to demonstrate how various techniques can be used to optimize training while still providing competitive performance in code generation and mathematical reasoning. In addition, latency testing conducted on a Distilled version of DeepSeek-V3, with approximately 14 billion parameters, running on a T4 GPU, reveals that although significant improvements have been made in optimizing latency there remains substantial barriers to deploying these models. Through this context, this research will serve as a reference document for practitioners and researchers who wish to understand current trends and challenges in increasing accessibility to high performance AI models.
Yassine Zouhdi, B. Hdioud· EPJ Web of Conferences· 0 citations
Evolutionary optimization of LLM prompts and agentic programs (e.g., GEPA) is dominated by fitness evaluation: scoring each candidate runs an answering LLM over a validation set, so the evaluator's price tier dictates total search cost. We restructure that search by decoupling the three roles an LLM plays, running the high-volume answering role on the cheapest tier, reserving a strong model for the rare reflection/variation operator, then exploiting upward cross-tier transfer to deploy the cheaply evolved prompt on a stronger target. We contribute a cost-controlled characterization of when cheap-tier search substitutes for target-tier search, and where it fails. Across four tasks (HotpotQA, IFBench, LiveBench-Math, HoVer) and eleven models in four model families, the resulting prompt matches or exceeds same-tier optimization while placing over 96% of search tokens on the cheapest tier, at 5.6-14x lower search cost, rising to 25-54x where reasoning tiers emit long chains of thought on every fitness call.
Tal Oved, Roi Pony, O. Naparstek et al.· 0 citations
Empirical results on RouterBench and SWE-Bench demonstrate that WR-Offline surpasses existing baselines in performance under a fixed budget and adheres more closely to budget constraints, and WR-Online achieves comparable performance to the baselines, while using substantially less exploration data.
Yi-Fei Li, Zi-Hui Gao, L. Lakshmanan· arXiv.org· 0 citations
FlavourBench is introduced, which instead compiles dense answer maps from a versioned culinary environment and remains similar under alternative metrics, task filters, family weights, and three public Epicure checkpoints.
J. Chen, Erim Hayretci· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
