Proves dimension-uniform KL bounds for exponential-integrator discretization of preconditioned ALD on Gaussian mixtures under spectral summability, showing EM stability restrictions are scheme-dependent rather than intrinsic.
hub
MIT press Cambridge, 2016
10 Pith papers cite this work. Polarity classification is still indexing.
hub tools
representative citing papers
OPT-SNG introduces a martingale model for SNG pruning in ANNS, proves O(n^{2/3+ε}) max out-degree and O(log n) expected path length, and gives a closed-form optimal truncation parameter that yields 5.9× average construction speedup.
A ray-tracing ultrasound simulator is made end-to-end differentiable, allowing automatic optimization of scene and system parameters from image-space losses.
A decoupled parametric PINN with conditional modulation and Rosenthal-derived output scaling achieves zero-shot thermal inference across arbitrary metal alloys in laser powder bed fusion.
ScaLoRA analytically derives per-update column scalings that let low-rank increments accumulate into high-rank weight updates, yielding faster convergence and higher accuracy than prior LoRA variants on LLMs up to 12B parameters.
A reference-free bootstrapped cross-validation method estimates performance of 4D deep-learning reconstruction from sparse X-ray data by comparing outputs from independent data subsets.
A layer-wise peeling framework creates reference bounds to diagnose under-optimized layers in trained decoder-only transformers, including low-bit and quantized versions.
paFEMU enables rapid constitutive model discovery by integrating sparse regression, physics augmentation, and finite element adjoint optimization on multi-modal data for interpretable transfer learning.
OpenCLIP-based gesture classification with linear probing controls AcoustoBot swarms at 87.8% accuracy and 3.95 s latency in controlled tests.
Supervised UMAP works well for classification but shows clear limitations in incorporating response information for regression tasks.
citing papers explorer
-
Dimension-Uniform Discretization Analysis of Preconditioned Annealed Langevin Dynamics for Multimodal Gaussian Mixtures
Proves dimension-uniform KL bounds for exponential-integrator discretization of preconditioned ALD on Gaussian mixtures under spectral summability, showing EM stability restrictions are scheme-dependent rather than intrinsic.
-
Sparse Neighborhood Graph-Based Approximate Nearest Neighbor Search Revisited: Theoretical Analysis and Optimization
OPT-SNG introduces a martingale model for SNG pruning in ANNS, proves O(n^{2/3+ε}) max out-degree and O(log n) expected path length, and gives a closed-form optimal truncation parameter that yields 5.9× average construction speedup.
-
Fully Differentiable Ultrasound Simulation Utilizing Ray-Tracing
A ray-tracing ultrasound simulator is made end-to-end differentiable, allowing automatic optimization of scene and system parameters from image-space losses.
-
Material-Agnostic Zero-Shot Thermal Inference for Metal Additive Manufacturing via a Parametric PINN Framework
A decoupled parametric PINN with conditional modulation and Rosenthal-derived output scaling achieves zero-shot thermal inference across arbitrary metal alloys in laser powder bed fusion.
-
ScaLoRA: Optimally Scaled Low-Rank Adaptation for Efficient High-Rank Fine-Tuning
ScaLoRA analytically derives per-update column scalings that let low-rank increments accumulate into high-rank weight updates, yielding faster convergence and higher accuracy than prior LoRA variants on LLMs up to 12B parameters.
-
An evaluation framework for sparse 4D (3D + time) imaging reconstruction via bootstrapped cross-validation
A reference-free bootstrapped cross-validation method estimates performance of 4D deep-learning reconstruction from sparse X-ray data by comparing outputs from independent data subsets.
-
Trust, but Verify: Peeling Low-Bit Transformer Networks for Training Monitoring
A layer-wise peeling framework creates reference bounds to diagnose under-optimized layers in trained decoder-only transformers, including low-bit and quantized versions.
-
Towards Rapid Constitutive Model Discovery from Multi-Modal Data: Physics Augmented Finite Element Model Updating (paFEMU)
paFEMU enables rapid constitutive model discovery by integrating sparse regression, physics augmentation, and finite element adjoint optimization on multi-modal data for interpretable transfer learning.
-
A Gesture-Based Visual Learning Model for Acoustophoretic Interactions using a Swarm of AcoustoBots
OpenCLIP-based gesture classification with linear probing controls AcoustoBot swarms at 87.8% accuracy and 3.95 s latency in controlled tests.
-
A Comparative Study of UMAP and Other Dimensionality Reduction Methods
Supervised UMAP works well for classification but shows clear limitations in incorporating response information for regression tasks.