Improved code translation by preserving structure with composed fine-tuning.
problem Improving code translation accuracy with unlabeled code outputs.
method Pre-trained denoiser to capture output structure, composed fine-tuning to fine-tune predictor.
result Composed fine-tuning significantly improves generalization over standard fine-tuning.
Unified approach to structured prediction combining entropy regularization and neuro-symbolic logic.
problem Structured prediction challenges due to large output spaces and insufficient labeled data.
method Neuro-symbolic entropy regularization loss that restricts entropy regularization to valid structures.
result Models predict more accurately and are more likely to be valid.
Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular structures still poses significant challenges. Crucially, state-of-the-art methods often …
Automatically identifies geometric flat outputs for robotic systems.
problem Lack of systematic and practical means to identify flat outputs for arbitrary robotic systems.
method Casts the search for a globally valid, equivariant flat output as an optimization problem using Riemannian geometry, Lie group theory, and differential forms.
result Approximate transcription of continuum formulation to a quadratic program achieves precise agreement with known closed-form flat outputs.
LLMs cause inconsistent financial outputs, smaller models are more reliable.
problem Inconsistent outputs from LLMs undermine auditability and trust in financial workflows.
method Finance-calibrated deterministic test harness, task-specific invariant checking, model classification, and cross-provider validation.
result Smaller models (Granite-3-8B, Qwen2.5-7B) achieve 100% output consistency, while larger models like GPT-OSS-120B have high drift.
New method uses spherical convolutional Wasserstein distance to validate climate models.
problem Ensuring the accuracy of global climate models.
method Spherical convolutional Wasserstein distance to measure model differences.
result Phase 6 models show modest improvements in realistic climatologies.
Enhanced conformal methods improve validity of LLM outputs.
problem Lack of conditional validity and high false rejection rates in LLM validity guarantees.
method Adaptive conditional conformal procedure and improved scoring function differentiation.
result Demonstrated improved validity and utility on real datasets.
TRACE improves conformal prediction for multi-dimensional outputs.
problem Challenges in constructing valid and informative conformal prediction regions for multi-dimensional outputs.
method TRACE uses transport alignment in diffusion and flow matching models to define nonconformity scores.
result TRACE yields valid and adaptive conformal prediction regions for multimodal and non-convex distributions.
Paper introduces conformal prediction for reliable uncertainty quantification in landmark localization.
problem Systematic underestimation of total predictive uncertainty in landmark localization.
method Conformal prediction framework for multi-output regression, generating flexible prediction regions.
result Methods outperform existing approaches in validity and efficiency across 2D and 3D datasets.
We introduce a new normalization technique that exhibits the fast convergence properties of batch normalization using a transformation of layer weights instead of layer outputs. The proposed technique keeps the contribution of positive and negative weights to the layer output balanced. We validate our method on a set o…
Proposes SHORE model for efficient MOR with sparsity and scalability.
problem Challenges of interpretability and scalability in MOR with high-dimensional outputs.
method Incorporates sparsity requirements and a two-stage optimization framework for efficient compression.
result Theoretical and empirical validation of the proposed framework's efficiency and accuracy.
VAIOM models financial returns using continuous input and categorical output.
problem Modeling continuous, noisy, and heterogeneous financial data.
method VAIOM is a decoder-only Transformer that separates input representation from output likelihood.
result VAIOM models outperform fixed single-bar LightGBM baseline in both Test halves.
We present the Latent Sequence Decompositions (LSD) framework. LSD decomposes sequences with variable lengthed output units as a function of both the input sequence and the output sequence. We present a training algorithm which samples valid extensions and an approximate decoding algorithm. We experiment with the Wall …
A method for constructing tight prediction intervals for multiple numerical outputs.
problem Constructing tight prediction intervals for multiple related numerical outputs.
method A novel coordinate-wise standardization procedure that makes residuals comparable across output dimensions, estimating suitable scaling parameters using calibration data.
result The method produces tighter prediction intervals than existing baselines while maintaining valid simultaneous coverage.
Approach selects variables and time intervals for comparing high-dimensional time-series data.
problem Comparing high-dimensional time-series data for significant differences.
method Data is split into subintervals, and two-sample tests are performed on each to identify distinguishing variables.
result The approach effectively identifies variables and time intervals where data significantly differs.
LLMs fail to match statistical ground truth despite stable run-to-run performance.
problem LLMs lack validation against statistical ground truth in automated scientific workflows.
method Introduced a behavioral evaluation framework for LLMs, separating four decision-making dimensions.
result LLMs can exhibit near-perfect stability but diverge from statistical ground truth.
Auto-regressive sequence-to-sequence models with attention mechanism have achieved state-of-the-art performance in many tasks such as machine translation and speech synthesis. These models can be difficult to train. The standard approach, teacher forcing, guides a model with reference output history during training. Th…
CITE algorithm provides anytime-valid certification of model outputs.
problem Challenges in controlling error levels in LLM self-consistency.
method Certification by Intersection-union Testing with E-processes (CITE) algorithm.
result Provable control of false certification at any prescribed level under arbitrary stopping rules.
Cross-validation is one of the most popular model selection methods in statistics and machine learning. Despite its wide applicability, traditional cross validation methods tend to select overfitting models, due to the ignorance of the uncertainty in the testing sample. We develop a new, statistically principled infere…
New measures for prediction validity and consonant plausibility introduced.
problem Challenges in predicting future observations and quantifying prediction uncertainty.
method Introducing Type-2 validity and using consonant plausibility measures and conformal prediction.
result Achieving both Type-1 and Type-2 validity through consonant plausibility measures and conformal prediction.
New method certifies risks of LLM outputs, improving accuracy and reliability.
problem Uncertain and incorrect outputs from large language models.
method Information-lift certificates using PAC-Bayes bounds and skeleton design.
result Achieves 77.0% coverage at 2% risk, outperforming baselines.
New approach ties loss curvature to model performance in deep learning.
problem Understanding the relationship between loss curvature and model performance in deep learning.
method Empirical analysis of loss Hessians and theoretical results on input-output Jacobians.
result Novel generalization bound in terms of empirical Jacobian.
Develops geometric framework for uncertainty-aware multi-class classification.
problem Silent failure of AI models when uncertain, especially in multi-class settings.
method Geometric framework treating probability vectors as points on the (c−1)-dimensional probability simplex, using Fisher--Rao metric for calibration and uncertainty quantification. result Empirical validation shows 72.5% of errors captured while deferring 34.5% of ambiguous predictions, reducing automated decision error rates from 16.8% to 6.9%.
Gaussian processes with differential privacy protect both inputs and outputs.
problem Previous DP methods only protected model outputs, not inputs.
method Sparse GP with private variational approximation, adjusting covariance for DP noise.
result Accurate models can be produced under strong privacy protection with sufficient data.
A new method for releasing AI workflows to avoid premature incorrect results.
problem Statistical challenges in releasing AI workflows with adaptive scoring.
method Wrapper that calibrates and accumulates evidence from high-scoring failures.
result Reduces premature incorrect release while still releasing on moderate evidence.
New method reveals how training data influence diffusion model outputs.
problem Difficulty in assessing training data impact on diffusion model outputs.
method Use of ensembles trained on carefully engineered splits of training data to identify influential training examples.
result Demonstrated the viability of ensembles as generative models and validity of assessing influence.
We consider the problem of joint modelling of metabolic signals and gene expression in systems biology applications. We propose an approach based on input-output factorial hidden Markov models and propose a structured variational inference approach to infer the structure and states of the model. We start from the class…
Deep generative models have achieved remarkable success in various data domains, including images, time series, and natural languages. There remain, however, substantial challenges for combinatorial structures, including graphs. One of the key challenges lies in the difficulty of ensuring semantic validity in context. …
Proposes FOAGP for efficient orthogonal effect decomposition of black-box computer experiments.
problem Challenges in sensitivity analysis of black-box computer experiments with complex, nonlinear functional outputs.
method Functional-output orthogonal additive Gaussian process (FOAGP) with conditional orthogonality constraint.
result Demonstrates effectiveness in orthogonal effect decomposition and variance decomposition through simulations and real-world application.
This paper introduces a novel approach to measuring privacy risks in deep computer vision models based on intermediate outputs.
problem The exposure of intermediate results in hidden layers of deep computer vision models poses significant privacy concerns.
method The approach leverages Degrees of Freedom (DoF) to evaluate the amount of information retained in each layer and combines this with the rank of the Jacobian matrix to assess sensitivity to input variations.
result The proposed framework provides deeper insights into privacy risks associated with intermediate representations without requiring adversarial attack simulations.
We proposed the expected energy-based restricted Boltzmann machine (EE-RBM) as a discriminative RBM method for classification. Two characteristics of the EE-RBM are that the output is unbounded and that the target value of correct classification is set to a value much greater than one. In this study, by adopting featur…
Early approaches to multiple-output Gaussian processes (MOGPs) relied on linear combinations of independent, latent, single-output Gaussian processes (GPs). This resulted in cross-covariance functions with limited parametric interpretation, thus conflicting with the ability of single-output GPs to understand lengthscal…
The generalization performance of kernel methods is largely determined by the kernel, but common kernels are stationary thus input-independent and output-independent, that limits their applications on complicated tasks. In this paper, we propose a powerful and efficient spectral kernel learning framework and learned ke…
Generative Augmented Inference improves AI-generated data for causal inference.
problem Challenges in using AI-generated annotations for reliable causal inference.
method Generative Augmented Inference (GAI) treats AI outputs as informative features for learning true labels, flexibly modeling the relationship using nonparametric methods.
result GAI significantly reduces estimation error and improves confidence interval quality compared to human-only and PPI-based methods.
Kernel methods are among the most popular techniques in machine learning. From a frequentist/discriminative perspective they play a central role in regularization theory as they provide a natural choice for the hypotheses space and the regularization functional through the notion of reproducing kernel Hilbert spaces. F…
Deep learning detects sleep state fluctuations in neonates from single EEG channel.
problem Monitoring sleep state fluctuations in neonatal intensive care units.
method Deep learning-based algorithm trained on 53 EEG recordings, validated on 30 polysomnography recordings.
result High accuracy (90%) in detecting quiet sleep states from single EEG channel, generalizing well to external dataset.
Industrial process control systems try to keep an output variable within a given tolerance around a target value. PID control systems have been widely used in industry to control input variables in order to reach this goal. However, this kind of Transfer Function based approach cannot be extended to complex processes w…
Extends machine learning model training to include validation data.
problem Machine learning validation data usage in training.
method Extends predictive information bottleneck to include validation data.
result Validation data improves model training efficiency.
Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these constraints and using them for supervision, bypassing the difficulty of using d…
AutoPC optimizes hyperparameters for the PC algorithm to improve its performance.
problem The unsupervised nature of the PC algorithm makes it difficult to tune the Type I α level. method AutoPC optimizes α directly for a chosen metric and ensures stability through a second run. result AutoPC consistently outperforms state-of-the-art methods across multiple metrics.
Sepsis is a poorly understood and potentially life-threatening complication that can occur as a result of infection. Early detection and treatment improves patient outcomes, and as such it poses an important challenge in medicine. In this work, we develop a flexible classifier that leverages streaming lab results, vita…
Two new methods improve efficiency of conformal predictive systems.
problem Efficiency of conformal predictive systems in regression problems.
method Split conformal predictive systems and cross-conformal predictive systems.
result Cross-conformal predictive systems are more efficient but not guaranteed valid.
Proposes a method for evaluating multiple dimensions of organizational effectiveness using DEA.
problem Evaluating multiple dimensions of organizational effectiveness in large data sets.
method Introduces two regularized DEA models (SBM and GP-SBM) to estimate both dimension-specific and aggregate efficiency scores.
result Demonstrates improved efficiency and validity compared to conventional methods.
Recurrent neural networks (RNNs) are powerful constructs capable of modeling complex systems, up to and including Turing Machines. However, learning such complex models from finite training sets can be difficult. In this paper we empirically show that RNNs can learn models of computer peripheral devices through input a…
Improved active output selection reduces calibration time by 10% or more.
problem Efficiently calibrate models with noisy data.
method Improved active output selection strategy considering noise estimate.
result At least 10% fewer measurements needed compared to existing strategies.
Proposes a method for explaining ranking decisions in learning systems.
problem Limited work on interpreting ranking decisions from learning systems.
method Model agnostic local explanation method using optimization to maximize validity.
result Approach outperforms other methods in validity across different LTR models.
We construct flexible likelihoods for multi-output Gaussian process models that leverage neural networks as components. We make use of sparse variational inference methods to enable scalable approximate inference for the resulting class of models. An attractive feature of these models is that they can admit analytic pr…
This paper provides a method for noise-calibrated inference from DP synthetic data.
problem Inference from DP synthetic data is often miscalibrated and lacks principled uncertainty quantification.
method Release DP sufficient statistics, perform noise-calibrated likelihood-based inference, and optional synthetic data generation.
result Asymptotic normality and valid confidence intervals for the plug-in DP MLE.