4 papers · 1 filter
Beyond Coordinate Gauge: An Audited Protocol for Detecting Donor-Specific Functional Fingerprints after Neural Collapse
Truong Xuan Khanh, Phan Thanh Duc
Independently trained neural networks have no shared neuron-index reference frame, so comparing them requires accounting for coordinate freedom. Neural Collapse sharpens this probl…
The Weight Norm Sets the Grokking Timescale: A Causal Delay Law
Truong Xuan Khanh, Doan Hoang Viet, Luu Duc Trung +1
Grokking is the delayed onset of generalization in neural networks, arising long after they fit the training data. Whether the weight norm causes this delay is disputed: some studi…
First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation
Truong Xuan Khanh, Truong Quynh Hoa, Luu Duc Trung +1
We give the first quantitative prediction of grokking delay under AdamW. Treating the delay as a first-passage time, we derive a closed-form law T_grok - T_mem = (1 / 2 kappa_LL et…
Spectral Entropy Collapse as a Phase Transition in Delayed Generalisation: An Interventional and Predictive Framework for Grokkin
Truong Xuan Khanh, Truong Quynh Hoa, Luu Duc Trung +1
Grokking - the delayed transition from memorisation to generalisation in neural networks - remains poorly understood. We study this phenomenon through the geometry of learned repre…