Can a simple yet effective algorithm be developed for estimating general exponential family distributions? There has been extensive prior work addressing this question.

"NIPS Neural Information Processing Systems 8-11th December 2014, Montreal, Canada",,, "Paper ID:","1711" "Title:","Distributed Bayesian Posterior Sampling via Moment Sharing" Current Reviews First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper proposes a new distributed Bayesian Posterior inference algorithm for big data, an important problem that has garnered a lot of attention in the last few years. The goal is to sample from the posterior distribution of model parameters theta given a dataset that is divided among m machines. The proposed distributed algorithm runs a separate Markov chain on each machine, each of which samples from a distribution proportional to p(Dm|theta) qm(theta) where Dm is the local data subset on machine m and qm is a variational (Gaussian) approximation to the product of similar factors on other machines. I think this is a great idea and addresses a very important problem. The paper is also relatively easy to understand. However, the experimental section is quite weak which makes me a little hesitant to argue strongly for acceptance.

Neural Networks can perform poorly when the training label distribution is heavily imbalanced, as well as when the testing data differs from the training distribution. In order to deal with shift in the testing label distribution, which imbalance causes, we motivate the problem from the perspective of an optimal Bayes classifier and derive a post-training prior rebalancing technique that can be solved through a KL-divergence based optimization. This method allows a flexible post-training hyper-parameter to be efficiently tuned on a validation set and effectively modify the classifier margin to deal with this imbalance. We further combine this method with existing likelihood shift methods, re-interpreting them from the same Bayesian perspective, and demonstrating that our method can deal with both problems in a unified way.

In this work, we propose Glow-TTS, a flow-based generative model for parallel TTS that does not require any external aligner.

Thanks all the reviewers for the detailed and thoughtful comments. HMM-based works [1, 2, 3], all of which proposed methods to estimate alignments from unsegmented data. We've not thoroughly explored to improve the duration predictor and simply follow the same We design the grouped 1x1 convolutions to be able to mix channels. For example, to generate a speech of 5.8 Therefore, adopting parallel TTS models significantly improves the sampling speed of end-to-end systems. In Section 5.3, we showed that varying temperature can change We will add a reference about Viterbi training.

Neural Information Processing Systems http://nips.cc/

These certificates map out-of-distribution examples to non-zero values, signaling epistemic uncertainty.

We consider the parameter estimation problem of a probabilistic generative model prescribed using a natural exponential family of distributions. For this problem, the typical maximum likelihood estimator usually overfits under limited training sample size, is sensitive to noise and may perform poorly on downstream predictive tasks. To mitigate these issues, we propose a distributionally robust maximum likelihood estimator that minimizes the worst-case expected log-loss uniformly over a parametric Kullback-Leibler ball around a parametric nominal distribution. Leveraging the analytical expression of the Kullback-Leibler divergence between two distributions in the same natural exponential family, we show that the min-max estimation problem is tractable in a broad setting, including the robust training of generalized linear models. Our novel robust estimator also enjoys statistical consistency and delivers promising empirical results in both regression and classification tasks.

However, animals often appear to behave suboptimally.

We study reinforcement learning problems where state observations are stochastically triggered by actions, a constraint common in many real-world applications. This framework is formulated as Action-Triggered Sporadically Traceable Markov Decision Processes (ATST-MDPs), where each action has a specified probability of triggering a state observation. We derive tailored Bellman optimality equations for this framework and introduce the action-sequence learning paradigm in which agents commit to executing a sequence of actions until the next observation arrives. Under the linear MDP assumption, value-functions are shown to admit linear representations in an induced action-sequence feature map. Leveraging this structure, we propose off-policy estimators with statistical error guarantees for such feature maps and introduce ST-LSVI-UCB, a variant of LSVI-UCB adapted for action-triggered settings. ST-LSVI-UCB achieves regret $\widetilde O(\sqrt{Kd^3(1-γ)^{-3}})$, where $K$ is the number of episodes, $d$ the feature dimension, and $γ$ the discount factor (per-step episode non-termination probability). Crucially, this work establishes the theoretical foundation for learning with sporadic, action-triggered observations while demonstrating that efficient learning remains feasible under such observation constraints.