A one-step curvature probe evaluates an initial direction, whereas continual learners are judged after reaching comparable new-task fit. In an overparameterized linearization, projected gradient descent converges to $\Delta_P=PJ^\top(JPJ^\top)^{-1}r$, and its squared-displacement inflation is exactly the reciprocal of...
Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Ibne Farabi Shihab, Md Najmus Swaqeeb· 0 citations
The demonstrated benefit is robust sparse advice volume on a useful task, not a proven per-state placement advantage, because the response-contingent metareasoning problem is formulated as a response-contingent metareasoning problem.
Ibne Farabi Shihab, Md Najmus Swaqeeb, Abu Sa-Adat Mohamed Moon-Im Al Ahsan· 0 citations
The perturbation analysis motivates pre-norm attention and MLP components under explicit local assumptions; results on AdaLN, U-shaped, convolutional, and cross-attention blocks are empirical transfer, not certified guarantees.
Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Anuj Sharma· 0 citations
A finite-width conditional bound linking the inverse participation ratio of squared singular values to central pre-softmax logit kurtosis is derived and a pointwise query--key product-tail target is defined and compared with independent factor surgery with a product-targeted factorization that preserves native attentio...
An explicit finite lower certificate for communicating MDPs is derived and an auditable composition rule for a span-constrained optimistic learner is given, and valid expectation conversion and constant comparability are formalized.
Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Md Najmus Swaqeeb· 0 citations
The evidence supports exact schema-induced conditioning, not a systems advantage over CARS, and the evaluated method makes no generic finite-trie scalability claim.
Ibne Farabi Shihab, Md Najmus Swaqeeb, Abu Sa-Adat Mohamed Moon-Im Al Ahsan· 0 citations
CODS is introduced, a critic-guided selector that alternates between fitting an algorithm-matched critic and acquiring high-residual transitions before freezing a reusable subset, a reusable selection procedure, not a formal coreset guarantee.
Ibne Farabi Shihab, Sanjeda Akter, Abu Sa-Adat Mohamed Moon-Im Al Ahsan et al.· 0 citations
The realizable share of oracle opportunity is small and certifiable: strong routers beat the best fixed model, and most of the gap remains, while the selection-valid confidence intervals are small and certifiable.
Ibne Farabi Shihab, Abu Sa-Adat Mohamed Moon-Im Al Ahsan, Md Najmus Swaqeeb· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.