paper-with-me

홈 › Papers

Robust Bi-Tempered Logistic Loss Based on Bregman Divergences

2019-06-08 · NeurIPS 2019 12 · Ehsan Amid, Manfred K. Warmuth, Rohan Anil, Tomer Koren

We introduce a temperature into the exponential function and replace the softmax output layer of neural nets by a high temperature generalization. Similarly, the logarithm in the log loss we use for training is replaced by a low temperature logarithm. By tuning the two temperatures we create loss functions that are non-convex already in the single layer case. When replacing the last layer of the neural nets by our bi-temperature generalization of logistic loss, the training becomes more robust to noise. We visualize the effect of tuning the two temperatures in a simple setting and show the efficacy of our method on large data sets. Our methodology is based on Bregman divergences and is superior to a related two-temperature method using the Tsallis divergence.

📄 PDF Abstract BibTeX arXiv:1906.03361

Code (11)

google/bi-tempered-loss 공식 구현 tf
Diulhio/bitemperedloss-tf tf
MindSpore-scientific-2/code-4/tree/main/bi-tempered-loss-pytorch mindspore
MindSpore-scientific-2/code-5/tree/main/bi-tempered-loss-pytorch mindspore
MindSpore-scientific-2/code-9/tree/main/bi-tempered-loss-pytorch mindspore
MindSpore-scientific/code-4/tree/main/bi-tempered-loss-pytorch mindspore
NingAnMe/Bi-Tempered-Logistic-Loss-PyTorch pytorch
fhopfmueller/bi-tempered-loss-pytorch pytorch
mlpanda/bi-tempered-loss-pytorch pytorch
prakashsellathurai/cassava-leaf-disease-classification pytorch
pwc-1/Paper-9/tree/main/4/bi-tempered-loss-pytorch mindspore

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Tempered Calculus for ML: Application to Hyperbolic Model Embedding

2024-02-06 · Richard Nock, Ehsan Amid, Frank Nielsen, Alexander Soen 외

Most mathematical distortions used in ML are fundamentally integral in nature: $f$-divergences, Bregman divergences, (regularized) optimal transport distances, integral probability metrics, geodesic distances, etc. In th…

Bias-variance decompositions: the exclusive privilege of Bregman divergences

2025-01-30 · Tom Heskes

Bias-variance decompositions are widely used to understand the generalization performance of machine learning models. While the squared error loss permits a straightforward decomposition, other loss functions - such as z…

Curved representational Bregman divergences and their applications

2025-04-08 · Frank Nielsen

By analogy to curved exponential families in statistics, we define curved Bregman divergences as Bregman divergences restricted to nonlinear parameter subspaces. We show that the barycenter of a finite weighted set of pa…

Symplectic Bregman divergences

2024-08-23 · Frank Nielsen

We present a generalization of Bregman divergences in symplectic vector spaces that we term symplectic Bregman divergences. Symplectic Bregman divergences are derived from a symplectic generalization of the Fenchel-Young…

A note on the quasiconvex Jensen divergences and the quasiconvex Bregman divergences derived thereof

2019-09-19 · Frank Nielsen, Gaëtan Hadjeres

We first introduce the class of strictly quasiconvex and strictly quasiconcave Jensen divergences which are oriented (asymmetric) distances, and study some of their properties. We then define the strictly quasiconvex Bre…