Latest Optimization Research Papers

The newest Optimization papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Optimization so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Optimizing In Vitro Maturation in Goats: A Comprehensive Evaluation of Follicular and Culture Factors
  Raashid Lateef Dar · mVedra · Jun 30, 2032

  Abstract not provided....

• Probing α-carboxysome biogenesis and modularity with bacterial microcompartment counterparts
  Ping Chang · University of Liverpool · Jan 1, 2029

  Bacterial microcompartments (BMCs) are protein-based organelles in prokaryotes that optimize metabolic pathways by confining specific enzymatic reactions within selectively permeable shells, playing critical roles in processes such as CO2 f…

• Performance Analysis of Solar-Powered Cooling Systems.
  Ahmed Abdellaoui · Zenodo (CERN European Organ... · Jul 9, 2028

  This technical report summarizes research conducted at the Solar Equipment Development Unit (UDES) regarding the integration of renewable energy in residential cooling systems. The study focuses on the experimental testing of solar thermal …

• Performance Analysis of Solar-Powered Cooling Systems.
  Ahmed Abdellaoui · Zenodo (CERN European Organ... · Jul 9, 2028

  This technical report summarizes research conducted at the Solar Equipment Development Unit (UDES) regarding the integration of renewable energy in residential cooling systems. The study focuses on the experimental testing of solar thermal …

• Deep q-learning aided k-means clustering protocol for optimizing network lifetime in wireless sensor networks
  Flynn Dowey · Open Collections · Jan 1, 2028

  The full abstract for this thesis is available in the body of the thesis, and will be available when the embargo expires....

• Optimization and Uncertainty in Learning: Optimizer, Regularization, and Randomized-Search Ablations on a Covertype PyTorch Backbone
  Makan Sabeti · Zenodo (CERN European Organ... · Jul 27, 2027
• Optimization and Uncertainty in Learning: Optimizer, Regularization, and Randomized-Search Ablations on a Covertype PyTorch Backbone
  Makan Sabeti · Zenodo (CERN European Organ... · Jul 27, 2027
• Data and Code for 'Air quality and health impacts of Data Center electricity demand in the United States'
  Yuang Chen · Zenodo (CERN European Organ... · Jan 1, 2027

  This repository contains the data, model inputs, simulation outputs, and analysis scripts used to quantify the air quality and public health impacts attributable to U.S. data center electricity demand in 2023. The analysis combines electric…

• MODELING AND CHARACTERIZATION OF ALGAL GROWTH IN ANAEROBIC DIGESTION WASTEWATER FOR PROCESS OPTIMIZATION
  S M Hasan Shahriar Rahat · Washington State University · Jan 1, 2027

  Microalgae cultivation using anaerobic digestion (AD) wastewater is an attractive way of producing nutrient-rich biomass and treating wastewater. Integration of computational modeling provides valuable insights into algal-bacterial interact…

• Data and Code for 'Air quality and health impacts of Data Center electricity demand in the United States'
  Yuang Chen · Zenodo (CERN European Organ... · Jan 1, 2027

  This repository contains the data, model inputs, simulation outputs, and analysis scripts used to quantify the air quality and public health impacts attributable to U.S. data center electricity demand in 2023. The analysis combines electric…

• Optimization of 5′ UTR mRNA regions for enhanced protein expression in therapeutic cell types
  Madelaine Kate Robertson · Open Collections · Jan 1, 2027

  The full abstract for this thesis is available in the body of the thesis, and will be available when the embargo expires....

• Gene Selection for Breast Cancer Classification Using T-Test Filtering and Wrapper-Based Optimization
  Abdelhamid Elwaer, Dreder Abdeladeem · Zenodo (CERN European Organ... · Dec 31, 2026
• Generative Marketing Mix Modeling: A Causal Inference Framework Linking GEO and GEM to Business Impact
  Masahiro Kato, Daiki Honma, Taka Kato · arXiv · Sep 10, 2026

  Generative artificial intelligence changes how firms reach customers, but standard marketing data do not record how often users see and notice a firm's name in generated answers. We develop Generative Marketing Mix Modeling (GMMM) to estima…

• AdamX: Cosine similarity meets gradient descent
  Francisco Caldas, Ruben Belo, Cláudia Soares · arXiv · Sep 10, 2026

  We introduce AdamX, a first-order optimizer that incorporates cosine similarity as an adaptive mechanism for controlling update magnitudes. The proposed method is scalable, model-agnostic, and straightforward to integrate into existing trai…

• Sparsity Regularized and Robust Mean Variance Portfolio Selection Under Ellipsoidal Uncertainty
  Deniz Akkaya, Emre Can Yayla, Buse Şen, Mustafa Ç. Pınar · arXiv · Sep 10, 2026

  We investigate mean-variance portfolio selection with an $\ell_0$-penalty to promote sparsity in asset allocations. Uncertainty in the mean return vector is incorporated through an ellipsoidal uncertainty set, yielding a robust sparse optim…

• Generalization Analysis of Distributed Kernel-based Robust Gradient Descent Algorithms
  Jun-Yi Meng, Zheng-Chu Guo, Yuan Mao · arXiv · Sep 10, 2026

  In this paper, we investigate the generalization performance of distributed gradient descent algorithms in a reproducing kernel Hilbert space under a robust loss function $l_σ$. By exploiting the spectral characterization of gradient descen…

• Silver Rate Is (Almost) Optimal for Gradient Descent Acceleration
  Yuhan Ye, Kaizhao Liu · arXiv · Sep 8, 2026

  We study how far gradient descent (GD) can be accelerated by predetermined nonnegative stepsizes in smooth convex optimization. Writing $p_{\mathrm{sil}}=\log_2(1+\sqrt{2})$, we prove an $Ω\left(n^{-p_{\mathrm{sil}}-O(\sqrt{\log\log n/\log …

• Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation
  Jiacheng Xu, Feng Chen, Xiuneng Xu, Bo An · arXiv · Sep 8, 2026

  Existing methods for test-time reinforcement learning (TTRL) derive rewards from answer-level self-voting on unlabeled test-time tasks with canonical answers, but this breaks down for code generation because programs cannot be compared by s…

• When Does Scale-Invariant Optimization Become Unstable? An Exact Schedule Law with Weight Decay
  Hasan Amin, Wei-Kai Chang, Rajiv Khanna · arXiv · Sep 8, 2026

  Normalization renders large parts of neural networks effectively scale invariant, inducing a hidden feedback loop in which learning-rate schedules and weight decay interact through the parameter norm to control the effective step taken by t…

• ThinkPrior: Zero-Rollout Difficulty Priors for Cold-Start Prompt Selection in RLVR
  Tommy Sha, Skylar Zhai, Siqi Zhao · arXiv · Sep 8, 2026

  In reinforcement learning with verifiable rewards (RLVR) trained with group relative policy optimization (GRPO), the KL-free reward-advantage term studied here depends on within-group reward variation. If all rollouts in a group are correct…

• Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCs
  Yujie Zhang, Huiying Lan, Ehsan Aghapour, Zhiyuan Ning et al. · arXiv · Sep 3, 2026

  As edge-based deep learning applications become more complex, optimizing performance on heterogeneous System-on-Chips (SoCs) presents unique challenges. Traditional pipelining techniques distributing the computation across different on-chip…

• Improved Gradient Descent Lower Bounds Beyond Nesterov
  Yuhan Ye, Kaizhao Liu · arXiv · Sep 2, 2026

  We study how far gradient descent (GD) can be accelerated by predetermined stepsizes in smooth convex optimization. Going beyond the classical $Ω(n^{-2})$ first-order oracle lower bound of Nemirovsky and Yudin, we prove an $Ω(n^{-1.6342})$ …

• UE5M3 FP4 Block Scaling for Stable Language Model Pretraining
  Robert Hu, Carlo Luschi, Paul Balanca · arXiv · Sep 2, 2026

  Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only a narrow range of magnitudes. NVIDIA's Transformer Engine \nv{} recipe addresses this with current-tensor scaling, a randomized Hadamard tra…

• LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates
  Dmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov · arXiv · Sep 2, 2026

  Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that…

• Gradient-Update Mismatch: Rethinking Conflict-Free Training of Physics-Informed Neural Networks
  Jing Xiao, Xinhai Chen, Qinglin Wang, Menghan Jia et al. · arXiv · Sep 1, 2026

  Training Physics-Informed Neural Networks (PINNs) requires jointly optimizing physics residual and initial/boundary condition loss terms, which often induce conflicting gradients. Gradient surgery methods mitigate this issue by constructing…

• Optimizing Byzantine Node Placement in Decentralized Federated Learning
  Edoardo Gabrielli, Gabriele Tolomei · arXiv · Sep 1, 2026

  Security evaluations of decentralized federated learning (DFL) typically focus on how Byzantine participants behave, while largely overlooking which participants are compromised. Yet, because aggregation is distributed over a communication …

• Rethinking Learnability in Offline Data-driven Optimization
  Chao Qian, Chen-Guang Wang, Rong-Xi Tan, Ke Xue · arXiv · Sep 1, 2026

  Black-Box Optimization (BBO) has found broad applications, but evolutionary algorithms and Bayesian optimization face efficiency challenges as real-world BBO problems grow increasingly complex. Data-driven optimization improves the efficien…

• Learning Sparse Decision Trees via Transformer Variational Auto-Encoders
  Giacomo Fidone, Alessio Cascione, Riccardo Guidotti · arXiv · Sep 1, 2026

  Decision trees are among the most widely used models in machine learning, largely due to their transparent decision logic, making them well-suited for high-stakes decision-making contexts. However, most existing learning algorithms focus on…

• Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization
  Camila Blank, Zhuofan Ying, Christopher Potts, Peter Hase et al. · arXiv · Aug 31, 2026

  Sycophantic agreement refers to a behavior in which language models excessively affirm the user, often at the cost of factual accuracy. Although sycophantic agreement is a well-known failure of model alignment, there is limited understandin…

• Normalized Low-Rank Adaptation
  Jiale Kang, Ziyin Yue, Zheng Zhan, Yangyi Huang et al. · arXiv · Aug 31, 2026

  While low-rank adaptation (LoRA) is widely used for parameter-efficient model adaptation, how to regularize its training dynamics for stable and effective optimization remains underexplored. Because LoRA initializes the up-projection to zer…