We introduce scalable algorithms for online learning of neural network parameters and Bayesian sequential decision making. Unlike classical Bayesian neural networks, which induce predictive uncertainty through a posterior over model parameters, our methods adopt a predictive-first perspective based on martingale posteriors. In particular, we work directly with the one-step-ahead posterior predictive, which we parameterize with a neural network and update sequentially with incoming observations. This decouples Bayesian decision-making from parameter-space inference: we sample from the posterior predictive for decision making, and update the parameters of the posterior predictive via fast, frequentist Kalman-filter-like recursions. Our algorithms operate in a fully online, replay-free setting, providing principled uncertainty quantification without costly posterior sampling. Empirically, they achieve competitive performance-speed trade-offs in non-stationary contextual bandits and Bayesian optimization, offering 10-100 times faster inference than classical Thompson sampling while maintaining comparable or superior decision performance.

We develop a predictive-first optimisation framework for streaming hidden Markov models. Unlike classical approaches that prioritise full posterior recovery under a fully specified generative model, we assume access to regime-specific predictive models whose parameters are learned online while maintaining a fixed transition prior over regimes. Our objective is to sequentially identify latent regimes while maintaining accurate step-ahead predictive distributions. Because the number of possible regime paths grows exponentially, exact filtering is infeasible. We therefore formulate streaming inference as a constrained projection problem in predictive-distribution space: under a fixed hypothesis budget, we approximate the full posterior predictive by the forward-KL optimal mixture supported on $S$ paths. The solution is the renormalised top-$S$ posterior-weighted mixture, providing a principled derivation of beam search for HMMs. The resulting algorithm is fully recursive and deterministic, performing beam-style truncation with closed-form predictive updates and requiring neither EM nor sampling. Empirical comparisons against Online EM and Sequential Monte Carlo under matched computational budgets demonstrate competitive prequential performance.

Further, we emphasize the significance of principled regularization of the network parameters and prediction.

The ability to encode informative functional beliefs in BNN priors can significantly reduce the bias and uncertainty of the posterior predictive, especially in regions of input space sparsely coveredbytraining data[27].

Further, we emphasize the significance of principled regularization of the network parameters and prediction.

We investigate neural network representations from a probabilistic perspective.

Previous work has shown that even in the infinite width limit, when NNs become GPs, there is no GP posterior interpretation to a deep ensemble trained with squared error loss.

We introduce scalable algorithms for online learning and generalized Bayesian inference of neural network parameters, designed for sequential decision making tasks. Our methods combine the strengths of frequentist and Bayesian filtering, which include fast low-rank updates via a block-diagonal approximation of the parameter error covariance, and a well-defined posterior predictive distribution that we use for decision making. More precisely, our main method updates a low-rank error covariance for the hidden layers parameters, and a full-rank error covariance for the final layer parameters. Although this characterizes an improper posterior, we show that the resulting posterior predictive distribution is well-defined. Our methods update all network parameters online, with no need for replay buffers or offline retraining. We show, empirically, that our methods achieve a competitive tradeoff between speed and accuracy on (non-stationary) contextual bandit problems and Bayesian optimization problems.