arXiv Machine Learning
Jacobian Rank Collapse in Decision-Focused Learning
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 4
When Do Surrogate Updates Improve Decisions? A Local Theory of Trajectory-Wise Transfer
arXiv:2608. 01130v1 Announce Type: new Abstract: A broad range of models face the mismatch where they are updated through trajectory losses but are evaluated by downstream task reward.
arXiv Computation and Language
3d ago
LARC: Low-Rank Adaptive Residual Connections for Learning in Frozen Models
arXiv:2609.40063v1 Announce Type: cross Abstract: Low-Rank Adaptive Residual Connections (LARC) give a frozen model a compact numerical state that can learn from feedback. The map $h+BAh$ adds a low-...
arXiv Machine Learning
Sep 4
The Gradient Does Not See Rank: Rank-Indifference in Matrix-CODI on ProsQA
The paper investigates whether the rank of latent matrices in matrix‑chain‑of‑thought (Matrix‑CODI) models influences performance on reasoning tasks. Across multiple training regimes on ProsQA and GSM8K‑Aug, rank‑k projection ablations show flat accuracy curves, indicating that truncating the latent matrix to low rank does not hurt performance. Experiments with various readout architectures—bilinear, bilinear‑plus‑GELU, SVD‑augmented, and quadratic—confirm that rank‑indifference persists even for nonlinear readouts, and a linear probe on the latent matrix underperforms a raw pretrained hidden state.
Hugging Face Trending Papers
Sep 1
Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation
Parameter-efficient fine-tuning is usually framed as a question of how many parameters to update. Under a severe trainable-state budget, however, where those coefficients act is equally consequential....
arXiv Machine Learning
Aug 6
The Loss Does Not See the Basis, but Adam Does
arXiv:2608. 05136v1 Announce Type: new Abstract: Gradient descent on a factored model $W = UV^\top$ is implicitly biased toward low-rank solutions, while Adam, starting from the same small initialization, is not.
arXiv Machine Learning
Sep 2
Frozen Cores Need Task Signal: Fisher-Whitened Cross-Covariance for Low-Resource LLM Adaptation
arXiv:2609.00762v1 Announce Type: new Abstract: Parameter-efficient fine-tuning is usually framed as a question of how many parameters to update. Under a severe trainable-state budget, however, where...