Robustly combines supervised and bandit feedback for contextual bandits.
problem Learning from mixed supervised and bandit data with potentially misaligned costs.
method Developed no-regret algorithms robust to misaligned cost distributions.
result Our approach is feasible and helpful in practice, as shown by empirical evaluations.
Unified model improves multi-task learning by accounting for temporal misalignment.
problem Poor predictive performance and uncertainty quantification due to temporal misalignment in multi-task learning.
method Uses Gaussian processes to model correlations and includes a monotonic warp of the input data to account for temporal misalignment.
result Improves predictive performance and uncertainty quantification in multi-task learning.
SpecGD mitigates misalignment in phase retrieval models with anisotropic inputs.
problem Misalignment during gradient descent in phase retrieval models with anisotropic inputs.
method Spectral gradient descent modifies gradient updates to preserve directional information and remove spike amplification.
result SpecGD removes spike amplification, leading to stable alignment and accelerated noise contraction.
Bayesian method corrects timing misalignment in recurrent event studies.
problem Estimating differences in event rates under two treatments with timing misalignment.
method g-computation procedure with joint semiparametric Bayesian model.
result Correctly estimates average causal effects under right-censoring.
No-knowledge alarms detect misaligned LLM judges without trusting them.
problem Monitoring LLM judges for consistency when ground truth is unknown.
method Formal logic and Linear Programming to detect disagreements.
result No false positives in detecting misaligned judges.
Emergent misalignment is influenced by training dynamics, model priors, and data.
problem Emergent misalignment in models
method Exploring training dynamics, model priors, and data
result Activation deltas before and after narrow fine-tuning correlate with their similarities when measured with the last prompt-token activations.
AI threatens financial stability through misuse and stealth adoption.
problem Misuse and stealth adoption of AI in financial regulations.
method Analysis of AI's potential risks and criteria for AI suitability.
result AI will likely become widely used by stealth, affecting high-level financial functions.
High-dimensional neural network manifolds misalign with human perception, causing adversarial examples.
problem Adversarial attacks fool neural networks, but their origin is unclear.
method Defined and analyzed a network's perceptual manifold (PM) for a class concept.
result Neural network PMs have orders of magnitude higher dimensions than natural human concepts, suggesting exponential misalignment.
New approach extracts AI model representations for steering and monitoring.
problem Understanding and steering AI models' internal knowledge representation.
method Feature learning advances for scalable linear concept representations.
result Concept representations enable steering and monitoring of AI models.
New method learns time-invariant rewards from demonstrations.
problem Learning robust rewards for tasks with varying execution times.
method Model-based inverse reinforcement learning with time-invariant costs.
result Approach enables learning from misaligned demonstrations and generalizes spatially.
GRASP removes spurious correlations in fine-tuned models, improving task performance and reducing bias.
problem Fine-tuned models can latch onto spurious correlations, leading to bias and reduced generalization.
method GRASP identifies and removes spurious correlations from model weights without removing latent factors.
result GRASP significantly reduces bias and improves task performance in various fine-tuning tasks.
Improves classifier evaluation by aligning with Total Classification Cost.
problem Lack of consensus on evaluation metrics and class imbalance issues.
method Introduces Weighted Accuracy (WA) and a reweighting framework for cost-sensitive scenarios.
result WA aligns with Total Classification Cost (TCC) minimization under realistic conditions.
Private anchors affect how information is communicated and can improve or distort transmission.
problem How private anchors influence strategic communication and information transmission.
method Analyzed a sender-receiver game with costly reports and privately observed anchors.
result Small positive reporting costs can lead to full revelation, even with zero costs.
Hallucinations in models are mislinked estimates, not errors.
problem Hallucinations in generative models as failures to link estimates to plausible causes.
method Formalized hallucinations, showed even optimal estimators hallucinate, provided a general lower bound on hallucinate rate, reframed hallucination as structural misalignment, and experimentally supported theory.
result Hallucinations are structural misalignments between loss minimization and human-acceptable outputs, leading to estimation errors.
A novel federated learning framework resolves structural misalignment in model fusion.
problem Structural misalignment in model fusion due to chaotic information distribution.
method Feature-oriented regulation method (Ψ-Net) to ensure feature information allocation and dedicated collaboration schemes. result Effective enhancement of federated learning applicability to heterogeneous settings with improved convergence speed, accuracy, and efficiency.
This paper proposed a bias-compensated normalized maximum correntropy criterion (BCNMCC) algorithm charactered by its low steady-state misalignment for system identification with noisy input in an impulsive output noise environment. The normalized maximum correntropy criterion (NMCC) is derived from a correntropy based…
AMEAN tackles BTDA by learning meta-sub-targets to bridge domain gaps and misalignments.
problem Blending-target Domain Adaptation (BTDA) with multiple sub-targets that are hard to distinguish.
method AMEAN uses two adversarial processes: first to align source and mixed target domains, second to learn meta-sub-targets.
result AMEAN significantly outperforms existing DA algorithms in BTDA scenarios.
SPACR trains uncertainty-aware regressors directly within a single pass, improving efficiency and validity.
problem Training uncertainty-aware regressors while maintaining efficiency and validity.
method Joint optimization of efficiency and validity during training.
result SPACR consistently provides tighter intervals and better coverage-efficiency trade-offs compared to standard CP and DOICR.
Reconstruction-based learning produces uninformative features for perception tasks.
problem Misalignment between reconstruction-based learning and perception tasks.
method Investigated the impact of input space reconstruction on feature learning for perception tasks.
result Reconstruction-based learning allocates model capacity to a subspace with uninformative features for perception tasks.
Study corrects misaligned cadaster maps using noisy supervision.
problem Correcting misaligned cadaster maps with noisy supervision data.
method Iterative training rounds to refine ground truth annotations.
result Reduces noise in cadaster map alignment datasets.
New method optimizes portfolios by dynamically integrating ESG constraints.
problem Static ESG scores mismatch sequential portfolio decisions.
method MACF-X, a family of adapters that learns ESG costs from multimodal evidence.
result Reduces tail ESG budget pressure while maintaining financial performance.
Microwave-based breast cancer detection has been proposed as a complementary approach to compensate for some drawbacks of existing breast cancer detection techniques. Among the existing microwave breast cancer detection methods, machine learning-type algorithms have recently become more popular. These focus on detectin…
Longitudinal patient data has the potential to improve clinical risk stratification models for disease. However, chronic diseases that progress slowly over time are often heterogeneous in their clinical presentation. Patients may progress through disease stages at varying rates. This leads to pathophysiological misalig…
Model proposes how regulators should oversee complex algorithms in high-stakes applications.
problem Regulating complex algorithms used in high-stakes applications like lending, testing, and hiring.
method Proposes a model where regulators are limited in learning about complex algorithms with misaligned preferences, and explores different regulatory approaches.
result Complex algorithms can improve welfare, but regulation should focus on the source of incentive misalignment for optimal results.
OmniMatch algorithm perfectly matches graphs without edge correlation.
problem Graph matching in the absence of edge correlation.
method OmniMatch algorithm for seeded multiple graph matching.
result OmniMatch aligns O(sα) unseeded vertices across multiple networks efficiently and perfectly. Study shows noisy data collection in ImageNet leads to biased model performance.
problem Noisy data collection in ImageNet datasets causes biased model performance.
method Human studies on ImageNet dataset to investigate design choices and their impact.
result Systematic misalignment between ImageNet benchmark and real-world task.
Theoretical justification for image inpainting using diffusion models.
problem Improving sample recovery in image inpainting without retraining.
method Analysis of RePaint algorithm and proposing RePaint+ to correct misalignment. result RePaint+ algorithm provably recovers the true sample with linear convergence. Study on reliability of latent reuse in diffusion models under distribution shift.
problem When can latent spaces from a source dataset be reused for a target dataset with different distributions?
method Considered a source-target setting with approximately low-dimensional datasets near different subspaces. Analyzed the target-domain score error due to principal-angle misalignment and target ambient noise.
result Latent reuse is reliable only if the source and target subspaces are close and the target ambient noise is not too amplified.
Proposes CCE to assess point-wise reliability of neural network predictions.
problem Overconfidence and misaligned predictive distributions in neural networks.
method Introduces Conditional Congruence (CCE) metric using conditional kernel mean embeddings.
result CCE exhibits correctness, monotonicity, reliability, and robustness in high-dimensional regression tasks.
ANN with GA optimizes flexible disc design for lower mass and stress.
problem Design flexible disc elements for lower mass and stress without compromising torque transmission and misalignment.
method Artificial Neural Network (ANN) coupled with Genetic Algorithm (GA) for design exploration.
result Optimized designs meet specified criteria with minimum mass and stress.
Power of network tests degrades when vertices are misaligned.
problem Power loss in network hypothesis testing due to vertex shuffling.
method Theoretical analysis and simulations of Frobenius norm differences in random dot product and stochastic block models.
result Shuffling vertices can significantly reduce the power of network tests.
Framework ensures alignment between humans and machines in LLMs.
problem Human-machine misalignment in LLMs scoring mechanisms.
method Lightweight calibration framework for blackbox models.
result Provably guarantees alignment between humans and machines.
PLUMAGE improves large model training efficiency and stability.
problem Accelerator memory and networking constraints during large model training.
method Probabilistic Low rank Unbiased Minimum Variance Gradient Estimator (PLUMAGE) that resolves bias and variance issues.
result PLUMAGE reduces training loss by 28% on average across the GLUE benchmark.
This paper tests LLMs in finance to assess ethical behavior.
problem Aligning AI with ethical and legal standards in finance.
method Prompted LLMs to simulate CEO behavior, analyzed with logistic regression.
result Significant heterogeneity in LLMs' unethical behavior propensity.
Success conditioning optimizes policies by imitating successful trajectories, solving a trust-region optimization problem.
problem Improving policies through random actions that lead to desired outcomes.
method Success conditioning, which involves collecting and updating policies based on successful trajectories.
result Success conditioning solves a trust-region optimization problem, maximizing policy improvement with a χ2 divergence constraint. Framework selects real estate redevelopment uses by integrating value, risk, complexity, and irreversibility.
problem Persistent underperformance of real estate assets due to structural misalignment.
method Integrates real-options logic and multi-criteria decision analysis.
result Reduces over-complexification and misalignment in strategic use selection.
Meta-learning framework for credit risk assessment of SMEs, aligning financial statement dates with evaluation dates.
problem Temporal misalignment of credit scoring models leading to bias and inconsistent predictions.
method Two-step temporal decomposition: static model for annual PDs, dynamic model for monthly PDs; stacking architecture to aggregate multiple models.
result Framework effectively captures credit risk evolution over time, improving temporal consistency and predictive stability.
Proposes continuous convolution layers for flexible feature map resizing.
problem Fixed stride limitations in discrete convolution layers.
method Introduces Continuous Convolution (CC) layers that use learned continuous functions.
result Dynamic and consistent resizing of feature maps at any scale, non-integer and axis-dependent.
OOD detection methods often misidentify OOD points, leading to ineffective safety improvements.
problem Improving model safety through OOD detection methods often leads to incorrect identification of out-of-distribution points.
method Re-examine popular OOD detection procedures based on predictive uncertainty or features of supervised models trained on in-distribution data.
result Popular OOD detection methods incorrectly conflate high uncertainty and far feature-space distance with being out-of-distribution.
This paper analyzes AJIVE for estimating shared subspace across multiple datasets, revealing its strengths and limitations.
problem Estimating shared subspace across multiple datasets with varying degrees of misalignment.
method Angle-based Joint and Individual Variation Explained (AJIVE) method, a two-stage spectral approach.
result AJIVE's performance in high signal-to-noise ratio (SNR) regimes and its non-diminishing error in low-SNR settings.
WassersteinGrad improves weather forecasting explanations by addressing geometric misalignment issues.
problem Improving explainability of autoregressive neural predictions on dynamic physical fields.
method WassersteinGrad, a geometric consensus method for averaged perturbed attribution maps.
result WassersteinGrad provides more accurate explanations for weather forecasting models.
Framework improves CATE estimation by aligning active learning with causal objectives.
problem High cost of outcome measurements limits CATE estimation.
method Causal-EPIG framework, targeting unobservable causal quantities.
result Strategies outperform standard baselines, revealing context-dependent optimal approaches.
LLMs struggle with zero-shot annotation tasks due to model-internalized priors.
problem Impact of model-internalized priors on LLM performance in zero-shot annotation tasks.
method Investigated three dimensions: familiarity, decision stickiness, and susceptibility to misaligned task definitions.
result Nearly two-thirds of zero-shot errors are resistant to correction, with a rescue rate of 34.8%. Definition-Specific Familiarity (DSF) shows a positive association with model performance.
There has been great interest recently in applying nonparametric kernel mixtures in a hierarchical manner to model multiple related data samples jointly. In such settings several data features are commonly present: (i) the related samples often share some, if not all, of the mixture components but with differing weight…
Paper introduces SDM for detecting LLM hallucinations, improving on entropy tests.
problem Challenges of Large Language Models (LLMs) with non-factual, nonsensical responses.
method Joint clustering on sentence embeddings to measure semantic divergence between prompts and responses.
result SDM framework detects deeper form of arbitrariness in LLM responses.
Many real world learning tasks involve complex or hard-to-specify objectives, and using an easier-to-specify proxy can lead to poor performance or misaligned behavior. One solution is to have humans provide a training signal by demonstrating or judging performance, but this approach fails if the task is too complicated…
We consider the problem of consistently matching multiple sets of elements to each other, which is a common task in fields such as computer vision. To solve the underlying NP-hard objective, existing methods often relax or approximate it, but end up with unsatisfying empirical performance due to a misaligned objective.…
Adversarial examples are due to non-robust features in data.
problem Understanding the reasons behind adversarial examples in machine learning.
method Developed a theoretical framework to identify non-robust features and demonstrated their widespread existence.
result Adversarial examples are a result of non-robust features in data.