Tootfinder

Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
Andreas Maurer, Erfan Mirzaei, Massimiliano Pontil
https://arxiv.org/abs/2510.06028 https…

Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
The paper provides data-dependent bounds on the test error of the Gibbs algorithm in the overparameterized interpolation regime, where low training errors are also obtained for impossible data, such as random labels in classification. The bounds are stable under approximation with Langevin Monte Carlo algorithms. Experiments on the MNIST and CIFAR-10 datasets verify that the bounds yield nontrivial predictions on true labeled data and correctly upper bound the test error for random labels. Our …

Comparing Contrastive and Triplet Loss in Audio-Visual Embedding: Intra-Class Variance and Greediness Analysis
Donghuo Zeng
https://arxiv.org/abs/2510.02161 https://

Comparing Contrastive and Triplet Loss in Audio-Visual Embedding: Intra-Class Variance and Greediness Analysis
Contrastive loss and triplet loss are widely used objectives in deep metric learning, yet their effects on representation quality remain insufficiently understood. We present a theoretical and empirical comparison of these losses, focusing on intra- and inter-class variance and optimization behavior (e.g., greedy updates). Through task-specific experiments with consistent settings on synthetic data and real datasets-MNIST, CIFAR-10-it is shown that triplet loss preserves greater variance within…

From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun, Mohammad Reza Nikoo, Fang Chen, Amir H. Gandomi
https://arxiv.org/abs/2509.21341

From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
We study symbolic surrogate modeling of frozen Transformer embeddings to obtain compact, auditable classifiers with calibrated probabilities. For five benchmarks (SST2G, 20NG, MNIST, CIFAR10, MSC17), embeddings from ModernBERT, DINOv2, and SigLIP are partitioned on the training set into disjoint, information-preserving views via semantic-preserving feature partitioning (SPFP). A cooperative multi-population genetic program (MEGP) then learns additive, closed-form logit programs over these views…