{"ID":2884591,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.06066","arxiv_id":"2508.06066","title":"Effective Sample Size and Generalization Bounds for Temporal Networks","abstract":"Learning from time series is fundamentally different from learning from i.i.d.\\ data: temporal dependence can make long sequences effectively information-poor, yet standard evaluation protocols conflate sequence length with statistical information. We propose a dependence-aware evaluation methodology that controls for effective sample size $N_{\\text{eff}}$ rather than raw length $N$, and provide end-to-end generalization guarantees for Temporal Convolutional Networks (TCNs) on $β$-mixing sequences. Our analysis combines a blocking/coupling reduction that extracts $B = Θ(N/\\log N)$ approximately independent anchors with an architecture-aware Rademacher bound for $\\ell_{2,1}$-norm-controlled convolutional networks, yielding $O(\\sqrt{D\\log p / B})$ complexity scaling in depth $D$ and kernel size $p$. Empirically, we find that stronger temporal dependence can \\emph{reduce} generalization gaps when comparisons control for $N_{\\text{eff}}$ - a conclusion that reverses under standard fixed-$N$ evaluation, with observed rates of $N_{\\text{eff}}^{-0.9}$ to $N_{\\text{eff}}^{-1.2}$ substantially faster than the worst-case $O(N^{-1/2})$ mixing-based prediction. Our results suggest that dependence-aware evaluation should become standard practice in temporal deep learning benchmarks.","short_abstract":"Learning from time series is fundamentally different from learning from i.i.d.\\ data: temporal dependence can make long sequences effectively information-poor, yet standard evaluation protocols conflate sequence length with statistical information. We propose a dependence-aware evaluation methodology that controls for...","url_abs":"https://arxiv.org/abs/2508.06066","url_pdf":"https://arxiv.org/pdf/2508.06066v3","authors":"[\"Barak Gahtan\",\"Alex M. Bronstein\"]","published":"2025-08-08T06:57:49Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[]","has_code":false}