In the high-dimensional limit the spherical Boltzmann machine admits exact equations for training dynamics, Bayesian evidence, and cascades of phase transitions tied to mode alignment with data, which connect to generative phenomena including double descent and out-of-equilibrium biases.
Advances in Neural Information Processing Systems , volume=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 11roles
background 3representative citing papers
Individually calibrated predictors become collectively miscalibrated under Brier-optimal strategic responses with positive belief correlations, but VCG aggregation restores dominant-strategy incentive compatibility and near-optimal performance.
Probability-of-Hit acquisition function ranks perturbation candidates by posterior probability of threshold exceedance, with asymptotic optimality proof and up to 6.4% gains on real immunology data.
Frame-level splits in MPI Sintel cause 1.6-2 dB performance inflation due to data leakage; scene-level protocols and a source-separable uncertainty model are proposed.
Temperature scaling of density-matrix eigenvalues from LLM semantic embeddings optimizes proper-score calibration and corrects systematic overconfidence so entropy equals risk.
In high-frequency market making, action robustness (Sinkhorn regularization) dominates uncertainty tolerance in reshaping sequential quoting and inventory, while excessive robustness can cut execution opportunities in illiquid names.
Plug-in losses approximate EDL training objectives at the Dirichlet mean with decaying error as evidence grows, including softmax under a specific mapping, and match classical EDL performance on Google Speech Commands.
ConfSleepNet introduces a conflict-aware evidential aggregation method for multi-modal sleep stage classification using hybrid category structures per modality to produce reliable joint decisions with uncertainty.
A model-agnostic two-stage estimator for conditional quantiles that represents the high-fidelity quantile as a low-fidelity quantile evaluated at a covariate-dependent level, with theory on faster convergence rates under shape similarity.
DisAAD trains a 1%-sized proxy model via adversarial distillation to quantify uncertainty in black-box LLMs by aligning with their output distributions.
Localization uncertainty visualization in AI predictions improves human annotation quality and speed by redirecting effort toward high-uncertainty boxes.
citing papers explorer
-
Spherical Boltzmann machines: a solvable theory of learning and generation in energy-based models
In the high-dimensional limit the spherical Boltzmann machine admits exact equations for training dynamics, Bayesian evidence, and cascades of phase transitions tied to mode alignment with data, which connect to generative phenomena including double descent and out-of-equilibrium biases.
-
When Individually Calibrated Models Become Collectively Miscalibrated
Individually calibrated predictors become collectively miscalibrated under Brier-optimal strategic responses with positive belief correlations, but VCG aggregation restores dominant-strategy incentive compatibility and near-optimal performance.
-
Many Needles in a Haystack: Active Hit Discovery for Perturbation Experiments
Probability-of-Hit acquisition function ranks perturbation candidates by posterior probability of threshold exceedance, with asymptotic optimality proof and up to 6.4% gains on real immunology data.
-
The frame-level leakage trap: rethinking evaluation protocols for intrinsic image decomposition, with source-separable uncertainty as a case study
Frame-level splits in MPI Sintel cause 1.6-2 dB performance inflation due to data leakage; scene-level protocols and a source-separable uncertainty model are proposed.
-
Eigenvalue Calibration for Semantic Embeddings of Large Language Models
Temperature scaling of density-matrix eigenvalues from LLM semantic embeddings optimizes proper-score calibration and corrects systematic overconfidence so entropy equals risk.
-
Robustness in Sequential Decision Making under Evolving Uncertainty: Evidence from High-Frequency Market Making
In high-frequency market making, action robustness (Sinkhorn regularization) dominates uncertainty tolerance in reshaping sequential quoting and inventory, while excessive robustness can cut execution opportunities in illiquid names.
-
Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier
Plug-in losses approximate EDL training objectives at the Dirichlet mean with decaying error as evidence grows, including softmax under a specific mapping, and match classical EDL performance on Google Speech Commands.
-
A Conflict-aware Evidential Framework for Reliable Sleep Stage Classification
ConfSleepNet introduces a conflict-aware evidential aggregation method for multi-modal sleep stage classification using hybrid category structures per modality to produce reliable joint decisions with uncertainty.
-
Multi-Fidelity Quantile Regression
A model-agnostic two-stage estimator for conditional quantiles that represents the high-fidelity quantile as a low-fidelity quantile evaluated at a covariate-dependent level, with theory on faster convergence rates under shape similarity.
-
Estimating the Black-box LLM Uncertainty with Distribution-Aligned Adversarial Distillation
DisAAD trains a 1%-sized proxy model via adversarial distillation to quantify uncertainty in black-box LLMs by aligning with their output distributions.
-
From Model Uncertainty to Human Attention: Localization-Aware Visual Cues for Scalable Annotation Review
Localization uncertainty visualization in AI predictions improves human annotation quality and speed by redirecting effort toward high-uncertainty boxes.