83 citations · 130 across the 28 of their papers we have counts for
8 papers · 1 filter
A Provably-Correct and Robust Convex Model for Smooth Separable NMF
Junjun Pan, Valentin Leplat, Michael Ng +1
Nonnegative matrix factorization (NMF) is a linear dimensionality reduction technique for nonnegative data, with applications such as hyperspectral unmixing and topic modeling. NMF…
Market-Driven Subset Selection for Budgeted Training
Ashish Jha, Valentin Leplat, AH Phan
Training large language models on massive datasets is computationally expensive, yet empirical evidence suggests that substantial portions of training examples contribute minimally…
GRAFT: Gradient-Aware Fast MaxVol Technique for Dynamic Data Sampling
Ashish Jha, Anh huy Phan, Razan Dibo +1
Training modern neural networks on large datasets is computationally and environmentally costly. We introduce GRAFT, a scalable in-training subset selection method that (i) extract…
Constrained Optimization via Constraint-Induced Geometry: Implicit Feasible Dynamics and Optimality from Stationarity
Valentin Leplat
We introduce Gravidy, a geometry-aware framework for constrained optimization in which constraints are encoded directly into the dynamics, so the motion remains feasible by constru…
Norm-Constrained Flows and Sign-Based Optimization: Theory and Algorithms
Valentin Leplat, Sergio Mayorga, Roland Hildebrand +1
Sign Gradient Descent (SignGD) uses only the coordinate-wise sign of the gradient. We study this method through norm-constrained continuous-time dynamics: at each point, the veloci…
Iterative Methods for Computing the Moore-Penrose Pseudoinverse of Quaternion Matrices, with Applications
Valentin Leplat, Salman Ahmadi-Asl, JunJun Pan +1
We develop quaternion--native iterative methods for computing the Moore--Penrose (MP) pseudoinverse of quaternion matrices and analyze their convergence. Our starting point is a da…
Pass-efficient Randomized Algorithms for Low-rank Approximation of Quaternion Matrices
Salman Ahmadi-Asl, Malihe Nobakht Kooshkghazi, Valentin Leplat
Randomized algorithms for low-rank approximation of quaternion matrices have gained increasing attention in recent years. However, existing methods overlook pass efficiency, the ab…
Nonnegative Tensor Decomposition Via Collaborative Neurodynamic Optimization
Salman Ahmadi-Asl, Valentin Leplat, Anh-Huy Phan +1
This paper introduces a novel collaborative neurodynamic model for computing nonnegative Canonical Polyadic Decomposition (CPD). The model relies on a system of recurrent neural ne…