LHCb reports the first upper limits on B0 → K+π−τ+τ− and Bs0 → K+K−τ+τ− branching fractions, with recast limits of 2.8×10−4 on B0 → K*(892)0 τ+τ− at 95% CL that improve prior bounds by an order of magnitude.
hub Mixed citations
Optuna: A Next-generation Hyperparameter Optimization Framework
Mixed citation behavior. Most common role is background (50%).
36
Pith papers citing it
Background
50% of classified citations
abstract
The purpose of this study is to introduce new design-criteria for next-generation hyperparameter optimization software. The criteria we propose include (1) define-by-run API that allows users to construct the parameter search space dynamically, (2) efficient implementation of both searching and pruning strategies, and (3) easy-to-setup, versatile architecture that can be deployed for various purposes, ranging from scalable distributed computing to light-weight experiment conducted via interactive interface. In order to prove our point, we will introduce Optuna, an optimization software which is a culmination of our effort in the development of a next generation optimization software. As an optimization software designed with define-by-run principle, Optuna is particularly the first of its kind. We will present the design-techniques that became necessary in the development of the software that meets the above criteria, and demonstrate the power of our new design through experimental results and real world applications. Our software is available under the MIT license (https://github.com/pfnet/optuna/).
hub tools
citation-role summary
background 3
dataset 2
method 1
citation-polarity summary
representative citing papers
ASAP integrates an LLM agent over a pool of HPO tools and adds system-level optimizations (prefix-stable prompts, speculation parallelism, Self-Tuner) to improve end-to-end wall-clock performance on diverse HPO tasks.
Patient-aware contrastive objective preserves per-patient SR structure in RR-interval embeddings, reaching 0.989 AUROC on patient-independent PAF detection with lower variance than SupCon or BCE baselines.
Kernel lock-in from SoC SDKs creates inherited vulnerability debt in SOHO devices, with SoC vendor community engagement as the viable mitigation strategy.
Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.
Deep neural networks reduce fitting uncertainties in CW-NMR polarization measurements for dynamically polarized targets.
Quantum reservoirs handle multivariate time series best with task-specific encodings that leverage non-classical effects.
First NLO-QCD amplitude-assisted ML regression for longitudinal-boson production rate in di-boson events at the LHC, benchmarked against random forests.
Machine learning cloud microphysics parameterization achieves stable decade-long online coupling in ICON with performance comparable to the classical graupel scheme while eliminating two tuning parameters.
RepSelect isolates forget-set-specific representations via gradient PCA collapse to achieve 4-50x better post-relearning robustness than baselines across multiple models and forget categories.
Rescaling merger trees with a halo-profile correction enables cheap generation of galaxy summary statistics across cosmologies using semi-analytic models, matching dedicated simulation accuracy with far fewer base runs.
A universal LLM optimizer for text artifacts achieves SOTA results on six tasks including tripling ARC-AGI accuracy and cutting cloud costs by 40% via cross-task transfer and side information.
PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.
A U-net with signed-distance transform loss achieves mean Dice scores of 0.96 on held-out and external MRI data for robust skull stripping in neuropathological cases.
TreeCoder improves LLM code generation accuracy by representing decoding as an optimizable tree search over programs with first-class constraints for syntax, style, and execution, outperforming baselines on MBPP and SQL-Spider.
Belle II sets upper limits between 1.3 and 2.5 times 10 to the minus 8 on branching fractions for four tau to e l l decay modes at 90 percent confidence level, the most stringent to date for four modes.
A new leaf-instance dataset for soybean-cotton detection and segmentation collected across growth stages and conditions from commercial farms is presented and validated with YOLOv11.
SSLA approximates the posterior predictive distribution by refitting Bayesian models on self-predicted data, yielding a deterministic uncertainty measure that outperforms standard Laplace approximations in calibration on regression tasks.
Tabular diffusion models leak membership information via attacks even with partial attacker knowledge, and common heuristic privacy metrics like distance-to-closest-record are unreliable.
CosmoPostProcess delivers simulation-calibrated radial corrections for projection-induced selection bias (20-40% amplitude near 1 h^{-1} Mpc) and baryonic effects in Euclid richness-selected cluster weak lensing profiles.
A new overdensity-conditioned emulator trained on small subvolumes from Quijote recovers the global halo mass function via integration over the overdensity distribution at 0.026% of the simulation cost.
Natural language embeddings of synthesis and testing conditions improve ML predictions of glass dissolution rates and enable generalization to out-of-distribution compositions with new elements.
No signal observed for B+ → π+ μ± e∓; branching fraction upper limit set at 1.8 × 10^{-9} at 90% CL.
In a controlled model with quadratic nonlinearity, field-level inference retains more parameter information than summaries up to 6-point functions as nonlinearity increases.
citing papers explorer
-
Searches for $B^0\to K^+\pi^-\tau^+\tau^-$ and $B_s^0\to K^+K^-\tau^+\tau^-$ decays
LHCb reports the first upper limits on B0 → K+π−τ+τ− and Bs0 → K+K−τ+τ− branching fractions, with recast limits of 2.8×10−4 on B0 → K*(892)0 τ+τ− at 95% CL that improve prior bounds by an order of magnitude.
-
ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments
ASAP integrates an LLM agent over a pool of HPO tools and adds system-level optimizations (prefix-stable prompts, speculation parallelism, Self-Tuner) to improve end-to-end wall-clock performance on diverse HPO tasks.
-
Patient-Aware Contrastive Learning Preserves Per-Patient Structure in RR-Interval Representations
Patient-aware contrastive objective preserves per-patient SR structure in RR-interval embeddings, reaching 0.989 AUROC on patient-independent PAF detection with lower variance than SupCon or BCE baselines.
-
Anchors that Don't Lift: Understanding Supply Chain Driven Kernel Lock-In and Governance-Mediated Mitigation Strategies in SOHO Devices
Kernel lock-in from SoC SDKs creates inherited vulnerability debt in SOHO devices, with SoC vendor community engagement as the viable mitigation strategy.
-
Learning Dynamic Stability Landscapes in Synchronization Networks
Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.
-
Polarized Target Nuclear Magnetic Resonance Measurements with Deep Neural Networks
Deep neural networks reduce fitting uncertainties in CW-NMR polarization measurements for dynamically polarized targets.
-
Multivariate quantum reservoir computing with discrete and continuous variable systems
Quantum reservoirs handle multivariate time series best with task-specific encodings that leverage non-classical effects.
-
Higher-order effects in amplitude-assisted polarisation extraction with machine-learning techniques
First NLO-QCD amplitude-assisted ML regression for longitudinal-boson production rate in di-boson events at the LHC, benchmarked against random forests.
-
From stable online coupling to decade-long climate simulations: A machine learning parameterization for cloud microphysics in ICON
Machine learning cloud microphysics parameterization achieves stable decade-long online coupling in ICON with performance comparable to the classical graupel scheme while eliminating two tuning parameters.
-
RepSelect: Robust LLM Unlearning via Representation Selectivity
RepSelect isolates forget-set-specific representations via gradient PCA collapse to achieve 4-50x better post-relearning robustness than baselines across multiple models and forget categories.
-
Learning the Universe with cosmological rescaling of merger trees and semi-analytic galaxy formation models
Rescaling merger trees with a halo-profile correction enables cheap generation of galaxy summary statistics across cosmologies using semi-analytic models, matching dedicated simulation accuracy with far fewer base runs.
-
optimize_anything: A Universal API for Optimizing any Text Parameter
A universal LLM optimizer for text artifacts achieves SOTA results on six tasks including tripling ARC-AGI accuracy and cutting cloud costs by 40% via cross-task transfer and side information.
-
PEML: Parameter-efficient Multi-Task Learning with Optimized Continuous Prompts
PEML co-optimizes continuous prompts and low-rank adaptations to deliver up to 6.67% average accuracy gains over existing multi-task PEFT methods on GLUE, SuperGLUE, and other benchmarks.
-
Efficient Brain Extraction of MRI Scans with Mild to Moderate Neuropathology
A U-net with signed-distance transform loss achieves mean Dice scores of 0.96 on held-out and external MRI data for robust skull stripping in neuropathological cases.
-
TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation
TreeCoder improves LLM code generation accuracy by representing decoding as an optimizable tree search over programs with first-class constraints for syntax, style, and execution, outperforming baselines on MBPP and SQL-Spider.
-
Search for the lepton-flavor-violating $\tau^{-} \rightarrow e^{\mp} \ell^{\pm} \ell^{\mp}$ decays at Belle II
Belle II sets upper limits between 1.3 and 2.5 times 10 to the minus 8 on branching fractions for four tau to e l l decay modes at 90 percent confidence level, the most stringent to date for four modes.
-
A Leaf-Level Dataset for Soybean-Cotton Detection and Segmentation
A new leaf-instance dataset for soybean-cotton detection and segmentation collected across growth stages and conditions from commercial farms is presented and validated with YOLOv11.
-
Self-Supervised Laplace Approximation for Bayesian Uncertainty Quantification
SSLA approximates the posterior predictive distribution by refitting Bayesian models on self-predicted data, yielding a deterministic uncertainty measure that outperforms standard Laplace approximations in calibration on regression tasks.
-
On Privacy Leakage in Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics
Tabular diffusion models leak membership information via attacks even with partial attacker knowledge, and common heuristic privacy metrics like distance-to-closest-record are unreliable.
-
Euclid preparation. CosmoPostProcess: A simulation calibrated framework for weak lensing selection bias in richness-selected galaxy clusters
CosmoPostProcess delivers simulation-calibrated radial corrections for projection-induced selection bias (20-40% amplitude near 1 h^{-1} Mpc) and baryonic effects in Euclid richness-selected cluster weak lensing profiles.
-
Efficiently emulating distribution functions in gigaparsec volumes for varying cosmological parameters
A new overdensity-conditioned emulator trained on small subvolumes from Quijote recovers the global halo mass function via integration over the overdensity distribution at 0.026% of the simulation cost.
-
Natural Language Embeddings of Synthesis and Testing conditions Enhance Glass Dissolution Prediction
Natural language embeddings of synthesis and testing conditions improve ML predictions of glass dissolution rates and enable generalization to out-of-distribution compositions with new elements.
-
Search for the lepton-flavour violating decays $B^+ \to \pi^+ \mu^\pm e^\mp$
No signal observed for B+ → π+ μ± e∓; branching fraction upper limit set at 1.8 × 10^{-9} at 90% CL.
-
Field-level vs summaries: convergence of information in non-Gaussian density fields
In a controlled model with quadratic nonlinearity, field-level inference retains more parameter information than summaries up to 6-point functions as nonlinearity increases.
-
Probabilistic Salary Prediction with Graph Attention Networks and a Mixture Density Network
GAT-MDN uses domain-specific graphs with GATs plus an MDN head to output conditional salary distributions and reports better NLL and MSE than an MLP-MDN baseline on a Dutch job dataset of over 1M records.
-
Star-formation variability on the star-forming main sequence during the Epoch of Reionization
PSD modeling of SFR scatter at six timescales shows dominant variability on 10-30 Myr scales, stronger in lower-mass galaxies at z=3-8.
-
Combating the Memory Walls: Optimization Pathways for Long-Context Agentic LLM Inference
PLENA introduces a co-designed system with three optimization pathways for long-context agentic LLM inference, claiming up to 2.23x throughput over A100 and 4.04x energy efficiency.
-
Inferring identified hadron production in $pp$ collisions with physics-informed machine learning at the LHC
A physics-informed neural network infers pT spectra of pi, K, p, Lambda, and Ks in unmeasured rapidity regions from PYTHIA8 pp collisions at 13.6 TeV, achieving 1.5-5.83% yield uncertainties while reproducing yield ratios and freeze-out parameters.
-
Optimizing Image Preparation and Compression for Face Recognition within 1024 Bytes
JPEG AI with optimized settings and preprocessing delivers the highest face recognition accuracy among tested codecs when compressing images to 1024 bytes.
-
Analysis of the $C\!P$ structure of the Yukawa coupling between the Higgs boson and tau leptons in proton-proton collisions at $\sqrt{s}$ = 13.6 TeV
Combined CMS result gives α^{Hττ} = 7 ± 16° for the CP mixing angle in H→ττ, consistent with SM expectation of 0 ± 14°.
-
Low-Magnification SEM May Suffice: Interpretable Deep Learning for Multi-Scale Fracture-Cause Classification in Zirconia-Toughened Alumina
A fine-tuned ViT on 8493 SEM images classifies fracture causes in zirconia-toughened alumina at 0.907 accuracy and 0.888 macro-F1, with comparable performance at 50x versus higher magnifications.
-
Improved Chase-Pyndiah Decoding for Product Codes with Scaled Messages
Scaling extrinsic messages by decoder confidence in Chase-Pyndiah decoding for product codes delivers a 0.1 dB gain over the baseline decoder.
-
VIGILant: an automatic classification pipeline for glitches in the Virgo detector
VIGILant applies tree-based models and a ResNet CNN to classify Virgo O3b glitches with 98% accuracy and has been deployed for daily use with an interactive dashboard.
-
PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction
PR3DICTR is a new open-access modular framework for 3D medical image classification and outcome prediction that works with as little as two lines of code.
-
Evaluating Local Explainability Metrics for Machine Learning Models on Tabular Data
Benchmark of local explainability methods on tabular data finds explanation quality driven primarily by dataset complexity rather than model predictive performance.
-
An Automatic Ground Collision Avoidance System with Reinforcement Learning
The paper designs a reinforcement learning-based automatic ground collision avoidance system for jet trainers that uses limited observations and line-of-sight terrain queries to prevent collisions.