Objective dimensionality sets the rank of task closure installed in a world-model latent; single-reward value equivalence is the rank-one corner of that law.
Reduced-rank regression for the multivariate linear model.Journal of Multivariate Analysis, 5(2):248–264
7 Pith papers cite this work, alongside 612 external citations. Polarity classification is still indexing.
7
Pith papers citing it
612
external citations · OpenAlex
representative citing papers
A spiked signal-plus-noise model yields separation ratios that partition multimodal problems into four regimes where alignment, prediction, both, or neither succeed.
SubFit enables better LLM compression by fitting residual bypasses to non-contiguously selected submodules, outperforming layer-granularity baselines in accuracy-perplexity trade-offs at 12.5-37.5% sparsity.
GPLFR jointly learns compression and GP regression for high-dimensional outputs, outperforming PCA-GP under structured noise and enabling a spatially resolved rocky-exoplanet climate emulator.
The authors propose target-space recovery profiles to diagnose which reproducible dimensions of fMRI brain responses are captured by model predictions, showing that accuracy alone can mask alignment mismatches in visual cortex.
Proposes PcovRnnp method enabling simultaneous dimension reduction and regularized coefficient estimation via nuclear norm penalty in high-dimensional settings.
Characteristic roots govern dynamics in linear forecasting models but noise induces spurious roots; rank reduction and Root Purge regularization mitigate this for more robust predictions.
citing papers explorer
-
The Rank-One Corner: How Much Value Equivalence Does a Task Need from a World Model?
Objective dimensionality sets the rank of task closure installed in a world-model latent; single-reward value equivalence is the rank-one corner of that law.
-
When to Align, When to Predict: A Phase Diagram for Multimodal Learning
A spiked signal-plus-noise model yields separation ratios that partition multimodal problems into four regimes where alignment, prediction, both, or neither succeed.
-
From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression
SubFit enables better LLM compression by fitting residual bypasses to non-contiguously selected submodules, outperforming layer-granularity baselines in accuracy-perplexity trade-offs at 12.5-37.5% sparsity.
-
Gaussian Process Latent Factor Regression for Low-Data, High-Dimensional Output Problems
GPLFR jointly learns compression and GP regression for high-dimensional outputs, outperforming PCA-GP under structured noise and enabling a spatially resolved rocky-exoplanet climate emulator.
-
Beyond Prediction Accuracy: Target-Space Recovery Profiles for Evaluating Model-Brain Alignment
The authors propose target-space recovery profiles to diagnose which reproducible dimensions of fMRI brain responses are captured by model predictions, showing that accuracy alone can mask alignment mismatches in visual cortex.
-
Principal Covariate Regression with Nuclear Norm Penalty
Proposes PcovRnnp method enabling simultaneous dimension reduction and regularized coefficient estimation via nuclear norm penalty in high-dimensional settings.
-
Characteristic Root Analysis and Regularization for Linear Time Series Forecasting
Characteristic roots govern dynamics in linear forecasting models but noise induces spurious roots; rank reduction and Root Purge regularization mitigate this for more robust predictions.