Discriminative Learning Of Similarity And Group Equivariant Representations

Abstract

One of the most fundamental problems in machine learning is to compare examples: Given a pair of objects we want to return a value which indicates degree of (dis)similarity. Similarity is often task specific, and pre-defined distances can perform poorly, leading to work in metric learning. However, being able to learn a similarity-sensitive distance function also presupposes access to a rich, discriminative representation for the objects at hand. In this dissertation we present contributions towards both ends. In the first part of the thesis, assuming good representations for the data, we present a formulation for metric learning that makes a more direct attempt to optimize for the k-NN accuracy as compared to prior work. We also present extensions of this formulation to metric learning for kNN regression, asymmetric similarity learning and discriminative learning of Hamming distance. In the second part, we consider a situation where we are on a limited computational budget i.e. optimi

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keytrivedi2018discriminative

Related papers

• Similarity Function Tracking Using Pairwise Comparisons (2017)2.26
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Similarity Learning Via Kernel Preserving Embedding (2019)10.35
• Neural Bregman Divergences For Distance Learning (2022)0.00
• Active Metric Learning And Classification Using Similarity Queries (2022)0.00
• Sparse Online Relative Similarity Learning (2021)2.26
• A New Similarity Space Tailored For Supervised Deep Metric Learning (2020)3.58
• Metric Learning In An RKHS (2025)0.00