More Like this

1. Bregman Gradient Policy Optimization

   Huang, Feihu; Gao, Shangqian; Huang, Heng (January 2022, The Tenth International Conference on Learning Representations (ICLR 2022))
2. Bregman Forward-Backward Operator Splitting

   https://doi.org/10.1007/s11228-020-00563-z  

   Bùi, Minh N.; Combettes, Patrick L. (December 2020, Set-Valued and Variational Analysis)

   null (Ed.)

   We establish the convergence of the forward-backward splitting algorithm based on Bregman distances for the sum of two monotone operators in reflexive Banach spaces. Even in Euclidean spaces, the convergence of this algorithm has so far been proved only in the case of minimization problems. The proposed framework features Bregman distances that vary over the iterations and a novel assumption on the single-valued operator that captures various properties scattered in the literature. In the minimization setting, we obtain rates that are sharper than existing ones. 

   more » « less
3. Bregman Plug-And-Play Priors

   https://doi.org/10.1109/ICIP46576.2022.9897933  

   Al-Shabili, Abdullah H.; Xu, Xiaojian; Selesnick, Ivan; Kamilov, Ulugbek S. (October 2022, IEEE International Conference on Image Processing (ICIP))

   The past few years have seen a surge of activity around integration of deep learning networks and optimization algorithms for solving inverse problems. Recent work on plug-and-play priors (PnP), regularization by denoising (RED), and deep unfolding has shown the state-of-the-art performance of such integration in a variety of applications. However, the current paradigm for designing such algorithms is inherently Euclidean, due to the usage of the quadratic norm within the projection and proximal operators. We propose to broaden this perspective by considering a non-Euclidean setting based on the more general Bregman distance. Our new Bregman Proximal Gradient Method variant of PnP (PnP-BPGM) and Bregman Steepest Descent variant of RED (RED-BSD) replace the traditional updates in PnP and RED from the quadratic norms to more general Bregman distance. We present a theoretical convergence result for PnP-BPGM and demonstrate the effectiveness of our algorithms on Poisson linear inverse problems. 

   more » « less
4. Accelerated Bregman operator splitting with backtracking

   https://doi.org/10.3934/ipi.2017048  

   Chen, Yunmei; Li, Xianqi; Ouyang, Yuyuan; Pasiliao, Eduardo (December 2017, Inverse Problems and Imaging)
5. Neural Bregman Divergences for Distance Learning

   Lu, Fred; Raff, Edward; Ferraro, Francis (May 2023, 11th International Conference on Learning Representations)

   Many metric learning tasks, such as triplet learning, nearest neighbor retrieval, and visualization, are treated primarily as embedding tasks where the ultimate metric is some variant of the Euclidean distance (e.g., cosine or Mahalanobis), and the algorithm must learn to embed points into the pre-chosen space. The study of non-Euclidean geometries is often not explored, which we believe is due to a lack of tools for learning non-Euclidean measures of distance. Recent work has shown that Bregman divergences can be learned from data, opening a promising approach to learning asymmetric distances. We propose a new approach to learning arbitrary Bergman divergences in a differentiable manner via input convex neural networks and show that it overcomes significant limitations of previous works. We also demonstrate that our method more faithfully learns divergences over a set of both new and previously studied tasks, including asymmetric regression, ranking, and clustering. Our tests further extend to known asymmetric, but non-Bregman tasks, where our method still performs competitively despite misspecification, showing the general utility of our approach for asymmetric learning. 

   more » « less