Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
hub Canonical reference
Angelopoulos and Stephen Bates
Canonical reference. 100% of citing Pith papers cite this work as background.
26
Pith papers citing it
297
external citations · Crossref
Background
100% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
years
2026 26roles
background 5polarities
background 5representative citing papers
Distribution-free predictive inference for individual treatment effects is impossible: any valid set must have infinite expected length under standard assumptions with continuous covariates.
Generative Robust Optimisation defines uncertainty sets via neural network decoders over latent spaces and evaluates them with a five-point framework, validated on planning problems using Wasserstein autoencoders.
AMLE graph value extensions meet a local action-gap certificate guaranteeing goal-reaching greedy rollouts under argmin-Q planning and achieve 0.97 success on AntMaze-derived graphs versus 0.58 for harmonic extension.
Embedding Temporal Logic (ETL) performs runtime monitoring directly in learned embedding spaces using distance-based predicates composed with temporal operators, supported by conformal calibration for reliable predicate evaluation.
SGC-RML creates an 8D symptom atlas from multimodal PD data and integrates conformal calibration to deliver reliable, rejectable longitudinal assessments.
Risk-controlled post-processing yields a threshold-structured policy that follows the baseline except where an oracle fallback sharply reduces conditional violation risk, achieving O(log n/n) expected excess risk in i.i.d. settings and exact risk control under exchangeability.
DualTCN is the first deep-learning model for time-domain marine CSEM inversion that regresses four earth parameters, achieves high accuracy on simulated data, and runs up to 21,000 times faster than classical optimizers.
Multiple-choice queries synthesized from Hoare triples enable more reliable identification of intended programs than labeled-example supervision in active learning for program disambiguation.
There exists a non-trivial Lipschitz constant L* that makes a network intrinsically calibrated; LiST finds it automatically via temperature feedback and produces calibrated robust models on CIFAR and Tiny-ImageNet.
For small AWJM process data, treating statistical curation as competing hypotheses, using multi-fold evaluation, and residual physics with GPs yields more stable rankings and calibrated uncertainty than single-split pure ML.
Decision-calibrated prediction sets learned via partially input-convex neural networks and calibrated with conformal risk control achieve closer adherence to constraint-satisfaction targets in robust DC optimal power flow than coverage-based sets.
Empirical Bayes conformal prediction converts score variability into r-value nonconformity scores that preserve target coverage while reducing inclusion of high-variance false candidates in image classification, CLIP VLMs, and LLMs.
Conformalized Quantum DeepONet Ensembles reduce operator inference from quadratic to linear complexity using QOrthoNNs and SPQCs while delivering distribution-free uncertainty guarantees through ensemble conformal prediction.
TA-CQR estimates a lower-tail allocation to shorten conformal intervals, but the abstract's regular-variation length formula is absent from the full text.
Bayesian deep learning method rankings are unreliable under data scarcity, reversing across datasets and sample sizes, and a hierarchical Bayesian framework with predictive detectability curves is needed to assess evaluation sufficiency.
ACoFi adaptively tunes the switching threshold of learned safety filters using conformal inference on the range of predicted safety values, asymptotically bounding the rate of incorrect safety assessments by a user parameter and reducing violations versus fixed thresholds in simulations.
Context Kubernetes formalizes six abstractions for knowledge orchestration in agentic AI, with experiments showing a three-tier permission model blocks all five tested attack scenarios where simpler baselines fail.
Uncertainty-aware RL for chemical language models raises true hit rate from 0.5 to 0.75 by favoring low-uncertainty regions during optimization.
A multiscale optimization method using explicit protein backbone geometry reconstructs atomic models from cryo-EM data, showing improved RMSD and TM scores on three simulated datasets.
Instrumented data augments observations with mechanistic models, uncertainty, and counterfactuals to enable causal interventions via Pearl's do-operator in scientific machine learning.
LoRA adapters enable a 61.47M-parameter aerodynamics Transformer pretrained on four vehicle families to adapt to a held-out fifth family with 20 samples, reaching R²=0.85 and outperforming full fine-tuning and from-scratch training with 3x more data.
Bayesian deep learning method rankings are unstable at small sample sizes, dataset-dependent, and require uncertainty-aware evaluation using hierarchical models and minimum detectable difference curves.
Reproduction of FACTER across architectures and sparsity levels shows static fairness instructions match dynamic prompt repair on semantic parity in fixed-candidate re-ranking, with code released.
citing papers explorer
-
The Statistical Cost of Adaptation in Multi-Source Transfer Learning
Multi-source transfer learning incurs an intrinsic adaptation cost that can exceed one, with phase transitions separating regimes where bias-agnostic estimators match oracle performance from those where they cannot.
-
Impossibility of Distribution-Free Predictive Inference for Individual Treatment Effects
Distribution-free predictive inference for individual treatment effects is impossible: any valid set must have infinite expected length under standard assumptions with continuous covariates.
-
Generative Robust Optimisation
Generative Robust Optimisation defines uncertainty sets via neural network decoders over latent spaces and evaluates them with a five-point framework, validated on planning problems using Wasserstein autoencoders.
-
Planner-Admissible Graph-PDE Value Extensions for Sparse Goal-Conditioned Planning
AMLE graph value extensions meet a local action-gap certificate guaranteeing goal-reaching greedy rollouts under argmin-Q planning and achieve 0.97 success on AntMaze-derived graphs versus 0.58 for harmonic extension.
-
Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic
Embedding Temporal Logic (ETL) performs runtime monitoring directly in learned embedding spaces using distance-based predicates composed with temporal operators, supported by conformal calibration for reliable predicate evaluation.
-
SGC-RML: A reliable and interpretable longitudinal assessment for PD in real-world DNS
SGC-RML creates an 8D symptom atlas from multimodal PD data and integrates conformal calibration to deliver reliable, rejectable longitudinal assessments.
-
Risk-Controlled Post-Processing of Decision Policies
Risk-controlled post-processing yields a threshold-structured policy that follows the baseline except where an oracle fallback sharply reduces conditional violation risk, achieving O(log n/n) expected excess risk in i.i.d. settings and exact risk control under exchangeability.
-
DualTCN: A Physics-Constrained Temporal Convolutional Network for 2 Time-Domain Marine CSEM Inversion
DualTCN is the first deep-learning model for time-domain marine CSEM inversion that regresses four earth parameters, achieves high accuracy on simulated data, and runs up to 21,000 times faster than classical optimizers.
-
Choose, Don't Label: Multiple-Choice Query Synthesis for Program Disambiguation
Multiple-choice queries synthesized from Hoare triples enable more reliable identification of intended programs than labeled-example supervision in active learning for program disambiguation.
-
LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks
There exists a non-trivial Lipschitz constant L* that makes a network intrinsically calibrated; LiST finds it automatically via temperature feedback and produces calibrated robust models on CIFAR and Tiny-ImageNet.
-
Physics-Informed Machine Learning Under Small-Data Constraints: Lessons from Abrasive Waterjet Milling
For small AWJM process data, treating statistical curation as competing hypotheses, using multi-fold evaluation, and residual physics with GPs yields more stable rankings and calibrated uncertainty than single-split pure ML.
-
Decision-calibrated prediction sets for robust power system operations
Decision-calibrated prediction sets learned via partially input-convex neural networks and calibrated with conformal risk control achieve closer adherence to constraint-satisfaction targets in robust DC optimal power flow than coverage-based sets.
-
Empirical Bayes Conformal Prediction for Vision and Language Models
Empirical Bayes conformal prediction converts score variability into r-value nonconformity scores that preserve target coverage while reducing inclusion of high-variance false candidates in image classification, CLIP VLMs, and LLMs.
-
Conformalized Quantum DeepONet Ensembles for Scalable Operator Learning with Distribution-Free Uncertainty
Conformalized Quantum DeepONet Ensembles reduce operator inference from quadratic to linear complexity using QOrthoNNs and SPQCs while delivering distribution-free uncertainty guarantees through ensemble conformal prediction.
-
Geometry of tail allocation in conformal prediction intervals
TA-CQR estimates a lower-tail allocation to shorten conformal intervals, but the abstract's regular-variation length formula is absent from the full text.
-
ProEval: Proactive Failure Discovery and Efficient Performance Estimation for Generative AI Evaluation
Bayesian deep learning method rankings are unreliable under data scarcity, reversing across datasets and sample sizes, and a hierarchical Bayesian framework with predictive detectability curves is needed to assess evaluation sufficiency.
-
Safe Control using Learned Safety Filters and Adaptive Conformal Inference
ACoFi adaptively tunes the switching threshold of learned safety filters using conformal inference on the range of predicted safety values, asymptotically bounding the rate of incorrect safety assessments by a user parameter and reducing violations versus fixed thresholds in simulations.
-
Context Kubernetes: Declarative Orchestration of Enterprise Knowledge for Agentic AI Systems
Context Kubernetes formalizes six abstractions for knowledge orchestration in agentic AI, with experiments showing a three-tier permission model blocks all five tested attack scenarios where simpler baselines fail.
-
Uncertainty-aware reinforcement learning for chemical language models
Uncertainty-aware RL for chemical language models raises true hit rate from 0.5 to 0.75 by favoring low-uncertainty regions during optimization.
-
Multiscale reconstruction of protein conformations from cryo-EM images
A multiscale optimization method using explicit protein backbone geometry reconstructs atomic models from cryo-EM data, showing improved RMSD and TM scores on three simulated datasets.
-
Instrumented data for causal scientific machine learning
Instrumented data augments observations with mechanistic models, uncertainty, and counterfactuals to enable causal interventions via Pearl's do-operator in scientific machine learning.
-
Adapting Automotive Aerodynamics Surrogates to New Vehicle Families via Transfer Learning
LoRA adapters enable a 61.47M-parameter aerodynamics Transformer pretrained on four vehicle families to adapt to a held-out fifth family with 20 samples, reaching R²=0.85 and outperforming full fine-tuning and from-scratch training with 3x more data.
-
Unstable Rankings in Bayesian Deep Learning Evaluation
Bayesian deep learning method rankings are unstable at small sample sizes, dataset-dependent, and require uncertainty-aware evaluation using hierarchical models and minimum detectable difference curves.
-
Reproducing FACTER: Fairness via Conformal Thresholding and Prompt Repair
Reproduction of FACTER across architectures and sparsity levels shows static fairness instructions match dynamic prompt repair on semantic parity in fixed-candidate re-ranking, with code released.
-
Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
A tutorial framing deep learning as a complement to optimization for sequential decision-making under uncertainty, with applications in supply chains, healthcare, and energy.
- Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with nonconform