Animals flexibly recombine a finite set of core motor motifs to meet diverse task demands, but existing behavior segmentation methods oversimplify this process by imposing discrete syllables under restrictive generative assumptions. To better capture the continuous structure of behavior generation, we introduce motif-based continuous dynamics (MCD) discovery, a framework that (1) uncovers interpretable motif sets as latent basis functions of behavior by leveraging representations of behavioral transition structure, and (2) models behavioral dynamics as continuously evolving mixtures of these motifs. We validate MCD on a multi-task gridworld, a labyrinth navigation task, and freely moving animal behavior. Across settings, it identifies reusable motif components, captures continuous compositional dynamics, and generates realistic trajectories beyond the capabilities of traditional discrete segmentation models. By providing a generative account of how complex animal behaviors emerge from dynamic combinations of fundamental motor motifs, our approach advances the quantitative study of natural behavior.

The Information Bottleneck (IB) objective uses information theory to formulate a task-performance versus robustness trade-off. It has been successfully applied in the standard discriminative classification setting. We pose the question whether the IB can also be used to train generative likelihood models such as normalizing flows. Since normalizing flows use invertible network architectures (INNs), they are information-preserving by construction. This seems contradictory to the idea of a bottleneck.

For the analysis of the Track-and-Stop strategy we derive a novel concentration inequality for Markov chains that may be of interest in its own right.

In this work, we propose a novel type of normalizing flow driven by a differential deformation of the Wiener process.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This is a theory heavy paper regarding the structure learning of antiferromagnetic Ising models. There are two main results in this paper. First, the authors, for the class of statistical algorithms introduced by Feldman et al, provided a computational lower bound for learning general graphical models on p nodes with maximum degree d. Second, the authors showed that a broad class of repelling models on general graphs can be learned using simple algorithms, even without the correlation decay property.

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

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper proposes projecting the parameters of an MRF onto the set of fast-mixing parameters: parameters for which MCMC quickly converges to the true distribution. The authors introduce a Euclidean projection operator that implements this property, but note that it can be difficult to apply. They then smooth it by requiring the projection to be close to an additional matrix input. This is sufficient for many cases, but can be applied repeatedly when the true Euclidean projection is required.

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

Some commonly used objective loss function such as cross-entropy loss for classification and squared loss for regression can be regarded as special cases of the logarithmic loss function.