6 papers · 1 filter
A statistical approach to bias in zero-shot learning: the lens of handwriting recognition
Clarence Chew, Gim Siang Chia, Sukalpa Chanda +2
Generalized zero-shot learning (GZSL) has emerged as an important paradigm for visual recognition systems that must generalize to classes that were not observed during training. Tr…
Determinantal sampling on general spaces: fast approximation via diffusion geometry
Hoang-Son Tran, Pranav Gupta, Subhroshekhar Ghosh
Determinantal point processes (DPPs) have recently emerged as a kernel-based alternative to standard independent sampling for constructing efficient minibatches, coresets, and othe…
State-of-art minibatches via novel DPP kernels: discretization, wavelets, and rough objectives
Hoang-Son Tran, Pranav Gupta, Rémi Bardenet +1
Determinantal point processes (DPPs) have emerged as a kernelized alternative to vanilla independent sampling for generating efficient minibatches, coresets and other parsimonious…
Negative Dependence as a toolbox for machine learning : review and new developments
Hoang-Son Tran, Vladimir Petrovic, Remi Bardenet +1
Negative dependence is becoming a key driver in advancing learning capabilities beyond the limits of traditional independence. Recent developments have evidenced support towards ne…
Small coresets via negative dependence: DPPs, linear statistics, and concentration
Rémi Bardenet, Subhroshekhar Ghosh, Hugo Simon-Onfroy +1
Determinantal point processes (DPPs) are random configurations of points with tunable negative dependence. Because sampling is tractable, DPPs are natural candidates for subsamplin…
Determinantal point processes based on orthogonal polynomials for sampling minibatches in SGD
Remi Bardenet, Subhro Ghosh, Meixia Lin
Stochastic gradient descent (SGD) is a cornerstone of machine learning. When the number N of data items is large, SGD relies on constructing an unbiased estimator of the gradient o…