Grokking arises from gradual amplification of a Fourier-based circuit in the weights followed by removal of memorizing components.
hub
The journal of machine learning research , volume=
11 Pith papers cite this work. Polarity classification is still indexing.
11
Pith papers citing it
hub tools
representative citing papers
RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
AmbiSuR adds intrinsic photometric disambiguation and a self-indication module to Gaussian Splatting to resolve ambiguities and improve surface reconstruction accuracy.
A fully differentiable TensorFlow gyrokinetic code allows approximate gradients of nonlinear turbulence quantities to be used for outer-loop tasks such as profile prediction despite stochasticity.
HORST uses non-commutative operator composition and a hyperbolic mirror map to combine stability from adaptive optimizers with L1 sparsity bias, outperforming AdamW across sparsity levels on vision and language tasks.
GCE-MIL is a backbone-agnostic wrapper that directly optimizes MIL evidence for sufficiency, necessity, and recoverability, yielding modest gains in Macro-F1 and C-index plus more faithful patch selection across many backbones and datasets.
SP-KV trains a utility predictor jointly with the LLM to dynamically prune low-utility KV cache entries, achieving 3-10x memory reduction during generation with negligible performance loss.
PnP-Corrector decouples physics simulation from error correction via a plug-and-play agent, cutting error by 29% in 300-day global ocean-atmosphere forecasts.
A recursive cubing framework identifies stable hyperparameter regions for MC dropout uncertainty quantification in spatial deep learning and produces competitive or superior predictive intervals versus a statistical baseline on simulations and land-surface temperature data.
Introduces a margin-adaptive confidence ranking method that learns an estimator from simulated diversity and derives margin-dependent generalization bounds for use in fixed-sequence testing of LLM-human agreement.
Covariance-aware ridge and combined l1-l2 regularizers for neural networks yield better predictive performance and complexity control than standard penalties in simulations and applications to cooling-load prediction and leukemia classification.
citing papers explorer
-
Progress measures for grokking via mechanistic interpretability
Grokking arises from gradual amplification of a Fourier-based circuit in the weights followed by removal of memorizing components.
-
Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation
RAT reformulates regularized natural policy gradients as vanilla gradients with a transformed advantage, computed efficiently via randomized block Kaczmarz iterations on on-policy data.
-
Revisiting Photometric Ambiguity for Accurate Gaussian-Splatting Surface Reconstruction
AmbiSuR adds intrinsic photometric disambiguation and a self-indication module to Gaussian Splatting to resolve ambiguities and improve surface reconstruction accuracy.
-
iGENE: A Differentiable Flux-Tube Gyrokinetic Code in TensorFlow
A fully differentiable TensorFlow gyrokinetic code allows approximate gradients of nonlinear turbulence quantities to be used for outer-loop tasks such as profile prediction despite stochasticity.
-
HORST: Composing Optimizer Geometries for Sparse Transformer Training
HORST uses non-commutative operator composition and a hyperbolic mirror map to combine stability from adaptive optimizers with L1 sparsity bias, outperforming AdamW across sparsity levels on vision and language tasks.
-
GCE-MIL: Faithful and Recoverable Evidence for Multiple Instance Learning in Whole-Slide Imaging
GCE-MIL is a backbone-agnostic wrapper that directly optimizes MIL evidence for sufficiency, necessity, and recoverability, yielding modest gains in Macro-F1 and C-index plus more faithful patch selection across many backbones and datasets.
-
Self-Pruned Key-Value Attention: Learning When to Write by Predicting Future Utility
SP-KV trains a utility predictor jointly with the LLM to dynamically prune low-utility KV cache entries, achieving 3-10x memory reduction during generation with negligible performance loss.
-
PnP-Corrector: A Universal Correction Framework for Coupled Spatiotemporal Forecasting
PnP-Corrector decouples physics simulation from error correction via a plug-and-play agent, cutting error by 29% in 300-day global ocean-atmosphere forecasts.
-
A Cubing Strategy for Identifying Stable Hyperparameter Regions for Uncertainty Quantification in Spatial Deep Learning
A recursive cubing framework identifies stable hyperparameter regions for MC dropout uncertainty quantification in spatial deep learning and produces competitive or superior predictive intervals versus a statistical baseline on simulations and land-surface temperature data.
-
Margin-Adaptive Confidence Ranking for Reliable LLM Judgement
Introduces a margin-adaptive confidence ranking method that learns an estimator from simulated diversity and derives margin-dependent generalization bounds for use in fixed-sequence testing of LLM-human agreement.
-
Adaptive Norm-Based Regularization for Neural Networks
Covariance-aware ridge and combined l1-l2 regularizers for neural networks yield better predictive performance and complexity control than standard penalties in simulations and applications to cooling-load prediction and leukemia classification.