Library · Optimization & control
What Parameter Optimization & Hyperparameter Tuning got wrong, from 38 theses
Summary written by a model from the records below: Across multiple machine learning and engineering applications, parameter optimization and hyperparameter tuning frequently encounter severe challenges such as overfitting, computational bottlenecks, and premature convergence. In many instances, complex tuning procedures and extended fine-tuning fail to outperform default configurations or simpler baseline methods. These records come from graduate theses, 2021 to 2026, each labeled with its degree where the repository states it, and each links to its thesis. They were extracted by language models reading the full text, so treat each as a lead to read, not a verdict.
Plus 10 problems the authors left open, listed at the end.
Failure modes, by theses reporting them
Select a mode to jump to its records.
Hyperparameter tuning and extended fine-tuning lead to overfitting and degraded out of sample generalization
Extended optimization and fine-tuning procedures frequently caused models to memorize training data, overfit noise, or treat genuine features as noise. Consequently, these tuned configurations degraded predictive accuracy on unseen data and underperformed simpler or zero-shot baselines.
Tried and failed
gradient-based hyperparameter optimization for sparse Gaussian processes applied to robotic manipulation dynamic modeling. Outcome: overfit. Reason: optimizers consistently overestimated signal variance, treating true functional features as noise
Decision-Making Architectures for Control of Uncertain Systems · Georgia Tech · PhD
Tried and failed
fine-tuning models solely on synthetic generated data applied to automatic speech recognition models. Outcome: overfit. Reason: training exclusively on synthetic data led to overfitting and degraded generalization to genuine speech
Voice conversion and text-to-speech for privacy protection applications · Imperial · PhD
Considered and rejected
Considered and rejected: Rejected manual divergence regularization parameter tuning (beta-NSF) in data-constrained inverse problems due to frequent severe underfitting or overfitting.
Breaking things so you don’t have to: risk assessment and failure prediction for cyber-physical AI · MIT · PhD
Considered and rejected
Considered and rejected: Rejected full unconstrained 10-sublayer free phase/amplitude parameter optimization due to severe parameter degeneracy and overfitting of noise.
Reflectivity ferromagnetic resonance for layer-resolved dynamic study of multi-layered systems · Oxford · PhD
Tried and failed
prolonged fine-tuning of pretrained diffusion models applied to medical image synthesis. Outcome: overfit. Reason: extended training caused catastrophic forgetting and overfitting, degrading reconstruction quality
Multi-contrast magnetic resonance imaging with deep generative learning · UT Austin · PhD
Tried and failed
fine-tuning pre-trained transformers with limited data applied to multivariate time series forecasting. Outcome: worse than baseline. Reason: overfitting to seasonal and occupancy patterns degraded performance below zero-shot baseline
Toward Transformer-based Large Energy Models for Smart Energy Management · Virginia Tech · Master's
Tried and failed
random forest hyperparameter tuning via grid search applied to time series error correction. Outcome: overfit. Reason: overemphasized lag-1 features, degrading downstream simulation accuracy and inflating variance
Tried and failed
random restarts for marginal likelihood hyperparameter optimization applied to Gaussian process regression. Outcome: overfit. Reason: higher marginal likelihood yielded models with poorer actual predictive accuracy
Accelerating HLS Autotuning of Large, Highly-parameterized Reconfigurable SoC Mappings · Penn · PhD
Tried and failed
physics-constrained hyperparameter optimization without cross-validation applied to time series prediction in volatile regimes. Outcome: overfit. Reason: Enforcing exact energy conservation caused condensed learning with near-perfect fit that degraded out-of-sample prediction.
LSSVR + PSO = MFG · Iowa State · PhD
Tried and failed
fine-tuning singular values with extended training applied to generative adversarial network adaptation. Outcome: overfit. Reason: Extended optimization caused training set memorization despite achieving misleadingly improved quantitative evaluation metrics.
Data-Efficient Learning in Image Synthesis and Instance Segmentation · Virginia Tech · Master's
Considered and rejected
Considered and rejected: Fine-tuning generative step models for >1 epoch, rejected due to detrimental overfitting.
Equipping language models for systematic reasoning · UT Austin · PhD
Considered and rejected
Considered and rejected: Rejected STRidge and LASSO in PDE-READ due to hyperparameter fine-tuning sensitivity and bias towards over-fitted solutions
Learning Differential Equations from Noisy, Limited Data · Cornell · PhD
Complex optimization and search procedures underperform simpler baselines or untuned default configurations
Automated techniques such as grid search, genetic algorithms, and Bayesian optimization were repeatedly beaten by random search, heuristic methods, or untuned default settings. Practitioners also observed that default hyperparameters preserved generalizability and avoided the variance inflation introduced by tuning.
Lost to a baseline
Kalman with GCV hyperparameter optimization performed worse than Savitzky-Golay gridsearched optima on several benchmark systems.
Open-Source Dynamical Systems Research, with a Side of (Francis) Bacon · University of Washington · PhD
Tried and failed
physics parameter domain randomisation applied to sim-to-real transfer in robot manipulation. Outcome: worse than baseline. Reason: did not outperform simpler random force injection despite requiring significantly higher tuning effort
Exploring sim-to-real transfer for learning-based robot manipulation · Imperial · Doctorate
Tried and failed
random forest Bayesian optimization for configuration tuning applied to runtime configuration optimization. Outcome: worse than baseline. Reason: direct flag-to-runtime mapping struggled to navigate high-dimensional configuration spaces effectively compared to random search
Accelerating regression testing through test environment tuning · UT Austin · PhD
Lost to a baseline
Random search with twice as many samples outperformed standard BO methods without gradient information on hyperparameter optimization tasks.
Advances in Sparse and Bayesian Optimization for Autonomous Scientific Discovery · Cornell · PhD
Considered and rejected
Considered and rejected: Rejected hyperparameter optimization of C and gamma for SVM in favor of default parameters because defaults achieved near-identical accuracy while preserving generalizability across multiple fusion schemes.
Fusion Approaches to Individual Tree Species Classification Using Multi-Source Remotely Sensed Data · York University · Master's
Lost to a baseline
In Experiment 2, Grid Search hyperparameter tuning of XGBoost (MSE 0.0078, R2 0.7602, MAPE 0.3912) and Genetic Algorithm tuning (MSE 0.0073, R2 0.7639, MAPE 0.3912) lost to the base untuned XGBoost model (MSE 0.0067, R2 0.7690, MAPE 0.3843).
Using Data Analytics and Machine Learning in Sustainable Forest Management from Remote Sensing Data · York University · Master's
Considered and rejected
Considered and rejected: Rejected hyperparameter tuning on RF error correction via out-of-bag error in favor of default parameters because it over-emphasized lag-1 error and worsened simulation variance.
Considered and rejected
Considered and rejected: Rejected Tree-structured Parzen Estimator (TPE) in favor of grid search for hyperparameter tuning due to inferior performance in initial testing.
Improving the Efficiency of Deep Reinforcement Learning based UAV Obstacle Avoidance with Edge AI · University College Dublin · PhD
Lost to a baseline
In Experiment 1, Grid Search hyperparameter tuning of XGBoost (R2 0.8600, MAPE 0.2647) and Genetic Algorithm tuning (R2 0.8635, MAPE 0.2689) lost to the base XGBoost model (R2 0.8738, MAPE 0.2525).
Using Data Analytics and Machine Learning in Sustainable Forest Management from Remote Sensing Data · York University · Master's
Lost to a baseline
Kalman smoothing with GCV hyperparameter optimization was outperformed by gridsearched Kalman smoothing and gridsearched Savitzky-Golay across multiple benchmark ODEs.
Open-Source Dynamical Systems Research, with a Side of (Francis) Bacon · University of Washington · PhD
Search algorithms and automated optimizers get trapped in poor local optima or exhibit training instability
Bayesian optimization, reinforcement learning search, and language model optimizers often suffered from premature convergence to suboptimal parameter regimes when exploration was low or expert priors were absent. Other automated tuning attempts were abandoned because hyperparameter sensitivity caused severe numerical and training instability.
Tried and failed
autonomous reinforcement learning parameter optimization without expert priors applied to chemical vapor deposition growth recipes. Outcome: did not converge. Reason: search frequently became trapped in poor local optima without human domain guidance
Synthesis and Applications of Large-Area Monolayer Graphene · MIT · PhD
Tried and failed
Bayesian optimization with low exploration parameter applied to neural stimulation parameter tuning. Outcome: did not converge. Reason: insufficient exploration led to premature convergence to suboptimal parameter regimes
A FRAMEWORK FOR DESIGNING DATA-DRIVEN OPTIMIZATION SYSTEMS FOR NEURAL MODULATION: WITH APPLICATIONS IN OPTOGENETIC AND ELECTRICAL BRAIN STIMULATION · Georgia Tech · PhD
Considered and rejected
Considered and rejected: Rejected Bayesian Optimization for hyperparameter tuning due to its tendency to get trapped in local optima rather than global optima.
Optimization of Reverse Supply Chain For End-of-life Products · Cranfield · PhD
Tried and failed
LLM-driven iterative runtime hyperparameter optimization applied to large language model serving inference. Outcome: did not converge. Reason: LLM optimizer became trapped in a suboptimal parameter subspace during iterative search
LLM-Guided Run-Time Parameter Optimization for Energy-Efficient Model Inference · Virginia Tech · Master's
Considered and rejected
Considered and rejected: Using DSSIM as a direct loss function for autoencoder training was rejected due to hyperparameter tuning instability in high-resolution, heterogeneous breast textures
Machine Learning Approaches to Improve Diagnosis and Management of Mammographic Calcifications · Duke · Doctorate
Considered and rejected
Considered and rejected: Rejected online test-time adaptation in favor of episodic per-core adaptation due to unstable hyperparameter tuning.
Towards High-Fidelity Prostate Tissue Characterization and Cancer Detection with Micro-Ultrasound and Deep Learning · Queen's University · PhD
Manual parameter tuning is rejected due to high labor requirements and risks of researcher bias
Authors frequently abandoned manual per-datapoint or per-scan tuning because it required intensive expert labor and introduced subjective bias. Adopting global configurations, automated optimizers, or neural network parameterizations instead preserved consistency across diverse inputs and imaging modalities.
Considered and rejected
Considered and rejected: Decided against application-specific hyperparameter fine-tuning to ensure strict generalizability across imaging modalities
Generalizable low-latency accelerated dynamic MRI · Iowa State · PhD
Considered and rejected
Considered and rejected: Rejected relying solely on manual feature engineering and hyperparameter tuning in favor of AutoML using H2O library to eliminate expert bias and intensive labor.
Machine learning (ml) approaches to model interdependencies between dynamic loads and crack propagation · Cranfield · PhD
Considered and rejected
Considered and rejected: Rejected manually tuning hyperparameters in favor of using the Adam optimizer with gradient descent.
Intelligent prediction of parameters of electric vehicles using artificial neural networks · University of Regina · Master's
Considered and rejected
Considered and rejected: Rejected per-scan tuning/optimization of hyperparameter α across varying collimations and object positions in the feasibility study in favor of a globally fixed calibration to prevent masking imaging nonidealities.
Algorithms for Quantitative Imaging with Advanced Cone-Beam Computed Tomography Configurations · Johns Hopkins · PhD
Considered and rejected
Considered and rejected: Treating strong convexity constants mu_i as tunable hyperparameters was rejected in favor of parametrizing a neural network mu_zeta(x, u) to eliminate manual per-datapoint hyperparameter tuning.
Engineering AI systems and AI for engineering: compositionality and physics in learning · UT Austin · PhD
Considered and rejected
Considered and rejected: Rejected using a running-window prior ensemble because small prior variance would require tuning ad-hoc variance inflation parameters across time steps without enough proxy data to prevent overfitting.
Quantifying changes in climate and surface elevation of polar ice sheets during the last glacial-interglacial transition · University of Washington · PhD
Hyperparameter optimization is abandoned due to excessive computational costs and poor scaling
Full hyperparameter searches and grid evaluations were frequently rejected because the parameter spaces were too large to explore feasibly. Authors noted that the substantial increases in tuning runtime outweighed any marginal accuracy improvements gained.
Considered and rejected
Considered and rejected: Rejected SMT/Max-Sat based parameter optimization for continuous control due to poor scalability, choosing Bayesian optimization instead
Programmatic reinforcement learning · UT Austin · PhD
Tried and failed
autoencoder on proper orthogonal decomposition coefficients applied to subsurface reservoir simulation. Outcome: worse than baseline. Reason: required extensive hyperparameter tuning, suffered poor consistency across scenarios, and ran slower than baselines
Fast modelling of gas reservoirs using non-intrusive reduced order modelling and machine learning · Imperial · PhD
Considered and rejected
Considered and rejected: Rejected grid search for hyperparameter tuning because it was computationally infeasible across the extensive parameter space.
A DATA-DRIVEN APPROACH TO PREDICTING AUSTRALIAN BUSHFIRES · Naval Postgraduate School · Master's
Considered and rejected
Considered and rejected: Rejected full hyper-parameter tuning of ML models because marginal accuracy gains were offset by large tuning time increases.
Program analysis for machine learning models · UT Austin · PhD
Considered and rejected
Considered and rejected: Neural networks were rejected for predicting phase behavior because they were less accurate than SVR/RF and required excessive hyperparameter tuning time.
Optimization of chemical enhanced oil recovery methods for naturally fractured carbonate reservoirs · UT Austin · PhD
Hyperparameter tuning fails to resolve errors caused by data outliers and regime changes
Optimizing hyperparameters failed to eliminate extreme prediction errors and struggled when exposed to bad leverage points or varying expiry dates. Standard objective functions like weighted least squares incurred severe bias in the presence of vertical outliers despite tuning attempts.
Tried and failed
standard Gaussian process regression applied to data with leverage points and outliers. Outcome: did not generalise. Reason: mean hyperparameter optimization via weighted least squares causes severe bias from vertical outliers and bad leverage points
Robust and Data-Driven Uncertainty Quantification Methods as Real-Time Decision Support in Data-Driven Models · Virginia Tech · Doctorate
Tried and failed
physics-constrained kernel regression with heuristic hyperparameter optimization applied to stochastic volatility modeling across expiries. Outcome: did not generalise. Reason: Failed to handle varying expiry dates even with additional parameter calibration
LSSVR + PSO = MFG · Iowa State · PhD
Tried and failed
extended hyperparameter optimization applied to time series regression with extreme outliers. Reason: tuning network hyperparameters failed to eliminate or reduce extreme prediction outlier errors
Machine Learning-Based Predictive Health Model of Turbofan Engine · Virginia Tech · Doctorate
Left open by the authors
Problems the authors named and did not get to.
Left open
Apply formal hyper-parameter optimization and overfitting safeguards to artificial neural networks used in adsorption process design. Blocker: No specific neural network architecture, baseline dataset, or optimization protocol is specified.
Computational design of multi-sorbent adsorption processes for post-combustion carbon capture · Imperial · PhD
Left open
Incorporate robust optimization techniques into simulated annealing optimal decision tree training and hyperparameter tuning to reduce overfitting to noisy data. Blocker: None
Left open
Develop initialization and hyperparameter tuning algorithms for ensemble regression methods to prevent overfitting. Blocker: None
A Sequential Modeling Approach to Explain Complex Processes and Systems · Virginia Tech · Doctorate
Left open
Develop and implement methods for optimal hyperparameter tuning for the ENF-ADBEL neural network. Blocker: Lack of specific optimization target, baseline performance criteria, or designated optimization methodology.
DESIGN OF FUZZY LOGIC-BASED INTEGRATED ADAPTIVE DECAYED BRAIN EMOTIONAL LEARNING NETWORKS FOR ONLINE TIME SERIES PREDICTION · Dalhousie · PhD
Left open
Implement automated hyperparameter optimization for the 3D-DDnet low-dose CT denoising architecture. Blocker: None
A 3D Deep Learning Architecture for Denoising Low-Dose CT Scans · Virginia Tech · Master's
Left open
Automate hyperparameter tuning for the ComputeCOVID19+ CT framework using IterML rather than perturb-and-observe methods. Blocker: None
Real-Time Computed Tomography-based Medical Diagnosis Using Deep Learning · Virginia Tech · Master's
Left open
Develop an automatic hyperparameter optimization approach for deep learning models predicting remaining useful life. Blocker: None
Optimisation of deep learning techniques on remaining useful life prediction of complex engineering systems · Cranfield · PhD
Left open
Develop an automated hyperparameter optimization method for automatic thresholding or SVD cutoff selection in 3D ultrasound super-resolution imaging. Blocker: None
Ultrafast 3-D ultrasound super-resolution imaging with a row-column array · Imperial · PhD
Left open
Incorporate Bayesian optimization, sequential experimental designs, and context information into hyperparameter tuning for image analysis models. Blocker: None
Statistical Methods for Performance Evaluation of Machine Learning and Artificial Intelligence Models · Virginia Tech · Doctorate
Left open
Implement automated hyperparameter tuning using grid search or Bayesian optimization for the CNN-Bi-LSTM prognostics model. Blocker: None
Intelligent Data-Driven Maintenance Planning for Marine Renewable Energy Systems · Dalhousie · Master's
Who has worked on this
Authors of the public theses cited on this page, most-cited first.
- Jacob Stevens-Haas · University of Washington · PhD · 2025
Open-Source Dynamical Systems Research, with a Side of (Francis) Bacon - Zach Brodeur · Cornell · PhD · 2023
HYDRO-METEOROLOGICAL UNCERTAINTY QUANTIFICATION FOR WATER RESOURCES PLANNING AND MANAGEMENT: ADVANCES IN SYNTHETIC FORECASTING AND STOCHASTIC WATERSHED MODELS - Polina Sysoeva · York University · Master's · 2023
Using Data Analytics and Machine Learning in Sustainable Forest Management from Remote Sensing Data - Ju heung Kim · Iowa State · PhD · 2022
LSSVR + PSO = MFG - Mary Katelyn Crumpacker · Virginia Tech · Master's · 2026
LLM-Guided Run-Time Parameter Optimization for Energy-Efficient Model Inference - Jin-sol Jung · Virginia Tech · Doctorate · 2026
Machine Learning-Based Predictive Health Model of Turbofan Engine - Zhien (Abigail) Wang · MIT · PhD · 2025
Synthesis and Applications of Large-Area Monolayer Graphene - J Bollard · Oxford · PhD · 2025
Reflectivity ferromagnetic resonance for layer-resolved dynamic study of multi-layered systems - Yueyan Gu · Virginia Tech · Master's · 2025
Toward Transformer-based Large Energy Models for Smart Energy Management - Patrick McEnroe · University College Dublin · PhD · 2025
Improving the Efficiency of Deep Reinforcement Learning based UAV Obstacle Avoidance with Edge AI - Hanbing Xia · Cranfield · PhD · 2025
Optimization of Reverse Supply Chain For End-of-life Products - Mohammad Mahdi Gilany Aslwarnoosfaderany · Queen's University · PhD · 2025
Towards High-Fidelity Prostate Tissue Characterization and Cancer Detection with Micro-Ultrasound and Deep Learning
Checking a claim in this area?
We can run the same search on any method or claim. If nothing turns up, we will say so, and that proves nothing on its own.