More Like this

1. Knowledge as a Breaking of Ergodicity

   https://doi.org/10.1162/neco_a_01741  

   He, Yang; Lubchenko, Vassiliy (March 2025, Neural Computation)

   Abstract We construct a thermodynamic potential that can guide training of a generative model defined on a set of binary degrees of freedom. We argue that upon reduction in description, so as to make the generative model computationally manageable, the potential develops multiple minima. This is mirrored by the emergence of multiple minima in the free energy proper of the generative model itself. The variety of training samples that employ N binary degrees of freedom is ordinarily much lower than the size 2N of the full phase space. The nonrepresented configurations, we argue, should be thought of as comprising a high-temperature phase separated by an extensive energy gap from the configurations composing the training set. Thus, training amounts to sampling a free energy surface in the form of a library of distinct bound states, each of which breaks ergodicity. The ergodicity breaking prevents escape into the near continuum of states comprising the high-temperature phase; thus, it is necessary for proper functionality. It may, however, have the side effect of limiting access to patterns that were underrepresented in the training set. At the same time, the ergodicity breaking within the library complicates both learning and retrieval. As a remedy, one may concurrently employ multiple generative models—up to one model per free energy minimum. 

   more » « less
2. Explanation as a Defense of Recommendation

   https://doi.org/10.1145/3437963.3441726  

   Yang, Aobo; Wang, Nan; Deng, Hongbo; Wang, Hongning (March 2021, Proceedings of the 14th ACM International Conference on Web Search and Data Mining)

   null (Ed.)

   Textual explanations have proved to help improve user satisfaction on machine-made recommendations. However, current mainstream solutions loosely connect the learning of explanation with the learning of recommendation: for example, they are often separately modeled as rating prediction and content generation tasks. In this work, we propose to strengthen their connection by enforcing the idea of sentiment alignment between a recommendation and its corresponding explanation. At training time, the two learning tasks are joined by a latent sentiment vector, which is encoded by the recommendation module and used to make word choices for explanation generation. At both training and inference time, the explanation module is required to generate explanation text that matches sentiment predicted by the recommendation module. Extensive experiments demonstrate our solution outperforms a rich set of baselines in both recommendation and explanation tasks, especially on the improved quality of its generated explanations. More importantly, our user studies confirm our generated explanations help users better recognize the differences between recommended items and understand why an item is recommended. 

   more » « less
3. Quantum coherence as a signature of chaos

   https://doi.org/10.1103/PhysRevResearch.3.023214  

   Anand, Namit; Styliaris, Georgios; Kumari, Meenu; Zanardi, Paolo (June 2021, Physical Review Research)

   null (Ed.)
4. Responsibility as a Foundation of Safety Culture

   https://doi.org/10.1021/acs.chas.3c00006  

   McMillion, Noah D.; Smith, Allison M.; Miller, Alexander J. (May 2023, ACS Chemical Health & Safety)
5. Parasitism as a potential driver of aposematism

   https://doi.org/10.1016/j.tree.2024.11.004  

   de_Roode, Jacobus C; Groot, Astrid T (March 2025, Trends in Ecology & Evolution)