arXiv:2610. 11475v1 Announce Type: new Abstract: Population gradient flow is a common tool for reasoning about how neural networks adapt, including after pretraining.
Population gradient flow is a common tool for reasoning about how neural networks adapt, including after pretraining. We show that it can mispredict finite-batch stochastic gradient descent (SGD) qual...
arXiv:2606. 21253v2 Announce Type: replace Abstract: Continual learning that is gradient-free, local, online, and append-only is attractive for edge and streaming deployment, but its value is usually argued informally.
The paper investigates how momentum methods affect large‑batch training in a one‑pass setting using power‑law kernel regression. It derives critical learning rates for SGD, Polyak, and Nesterov, and shows how these rates depend on batch size, momentum, and model capacity. The authors provide scaling laws for risk dynamics, a three‑regime batch‑size phase diagram, and demonstrate that Polyak increases the critical batch size while Nesterov improves data efficiency in the large‑batch regime.
arXiv:2605. 24316v2 Announce Type: replace Abstract: Scaling laws provide compact descriptions of how prediction error varies with compute, model size, and data, but existing theory mainly treats single-sample SGD or full data reuse, leaving the role of mini-batching unclear.
arXiv:2609.36945v1 Announce Type: new Abstract: We study the learning dynamics of fine-tuning a policy model on self-generated and reward-weighted data, with particular focus on a generalized version...
arXiv:2607. 04113v1 Announce Type: new Abstract: Diffusion and flow-matching samplers integrate a learned probability-flow ODE from a large noise scale down to a small terminal floor $\sigma_{\min}$, at which the score is stiff and the flow develops a boundary layer.
The paper demonstrates that diffusion models encode memorization in the geometry of their learned energy landscape before it becomes visible in generated samples. By analyzing score divergence and basin volume, the authors show that localized basins form around training images early in training, and that cyclic denoising can recover these images even when one‑shot generation shows no copies. Experiments on Gaussian mixtures, CelebA, CIFAR‑10, and Stable Diffusion v1.4 confirm that basin geometry reveals memorization across various settings.
Diffusion and flow-matching samplers integrate a learned probability-flow ODE from a large noise scale down to a small terminal floor $σ_{\min}$, at which the score is stiff and the flow develops a boundary layer. We treat $σ_{\min}$ as a singular-perturbation parameter and determine which fixed-step samplers are asymptotic-preserving (AP), that is, stable and uniformly accurate as $σ_{\min}\to0$, casting the criteria as an a posteriori audit: residual functionals with $σ_{\min}$-uniform coefficients, computable on a pretrained checkpoint without ground-truth scores or exact trajectories.
The paper identifies a problem called Gradient-Update Mismatch (GUM), where optimizers can alter conflict-free gradient directions produced by gradient surgery, leading to conflicts between physics residual and boundary condition losses in Physics-Informed Neural Networks (PINNs). To address this, the authors propose Gradient-Update Alignment (GUA), which projects the optimizer’s update onto the conflict-free cone and adjusts internal optimizer state accordingly. Experiments show GUM is common across many optimizers, and GUA consistently eliminates conflicts and significantly reduces error in PINN training.
arXiv:2607. 07538v1 Announce Type: new Abstract: Training a model with noisy gradient descent can be idealized as overdamped Langevin dynamics on the loss landscape, and a natural safety question is to bound the probability $\nu_t(\mathcal{A}_H) = \mathbb{P}(Q_t \in \mathcal{A}_H)$ that the trajectory lies in a designated failure region $\mathcal{A}_H$.
The paper investigates how momentum methods affect large‑batch training in a one‑pass setting using power‑law kernel regression. It derives critical learning rates for SGD, Polyak, and Nesterov, and shows how these rates depend on batch size, momentum, and a capacity exponent. The authors then analyze risk dynamics, optimize final‑step risk under a fixed data budget, and present a three‑regime batch‑size phase diagram that highlights Polyak’s ability to enlarge the critical batch size and Nesterov’s superior data efficiency in the large‑batch regime.
arXiv:2608. 07922v1 Announce Type: new Abstract: Adaptive learning needs both a state that preserves what observations imply and opportunities to act on that state.