An Exact Kernel Equivalence for Finite Classification Models — HN submission

Fri, 15 Sep 2023 19:47:22 GMT

An Exact Equivalence for Finite Classification Models

2 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.

An Exact Kernel Equivalence for Finite Classification Models — mentioned by bwbellmath

Fri, 15 Sep 2023 19:30:20 GMT

See our re-examination of the kernel equivalence. Path kernels exactly measure how models learn as their understanding of data improves during training, and this can be expressed in terms of the gradients with regards to each trianing input: https://arxiv.org/abs/2308.00824 We believe that all neural networks are effectively an SVM or more generally reproducing kernel architecture to implicitly layer the understanding contributed during each training iteration. Do you have any comment in the RKHS or RKBS context for transformers?

Paper and discussion history. A mention is not an endorsement.

An Exact Kernel Equivalence for Finite Classification Models · HackerPapers discussions

An Exact Kernel Equivalence for Finite Classification Models — HN submission

An Exact Kernel Equivalence for Finite Classification Models — mentioned by bwbellmath