18 citations · 44 across the 11 of their papers we have counts for
11 papers
Cooper: A Library for Constrained Optimization in Deep Learning
Jose Gallego-Posada, Juan Ramirez, Meraj Hashemizadeh +1
Cooper is an open-source package for solving constrained optimization problems involving deep learning models. Cooper implements several Lagrangian-based first-order update schemes…
Feasible Learning
Juan Ramirez, Ignacio Hounie, Juan Elenter +4
We introduce Feasible Learning (FL), a sample-centric learning paradigm where models are trained by solving a feasibility problem that bounds the loss for each training sample. In…
On PI Controllers for Updating Lagrange Multipliers in Constrained Optimization
Motahareh Sohrabi, Juan Ramirez, Tianyue H. Zhang +2
Constrained optimization offers a powerful framework to prescribe desired behaviors in neural network models. Typically, constrained problems are solved via their min-max Lagrangia…
Balancing Act: Constraining Disparate Impact in Sparse Models
Meraj Hashemizadeh, Juan Ramirez, Rohan Sukumaran +3
Model pruning is a popular approach to enable the deployment of large deep learning models on edge devices with restricted computational or storage capacities. Although sparse mode…
A Distributed Data-Parallel PyTorch Implementation of the Distributed Shampoo Optimizer for Training Neural Networks At-Scale
Hao-Jun Michael Shi, Tsung-Hsien Lee, Shintaro Iwasaki +5
Shampoo is an online and stochastic optimization algorithm belonging to the AdaGrad family of methods for training neural networks. It constructs a block-diagonal preconditioner wh…
Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints
Jose Gallego-Posada, Juan Ramirez, Akram Erraqabi +2
The performance of trained neural networks is robust to harsh levels of pruning. Coupled with the ever-growing size of deep learning models, this observation has motivated extensiv…
Lonie: Compressing COINs with L-constraints
Juan Ramirez, Jose Gallego-Posada
Advances in Implicit Neural Representations (INR) have motivated research on domain-agnostic compression techniques. These methods train a neural network to approximate an object,…
Equivariant Mesh Attention Networks
Sourya Basu, Jose Gallego-Posada, Francesco Viganò +2
Equivariance to symmetries has proven to be a powerful inductive bias in deep learning research. Recent works on mesh processing have concentrated on various kinds of natural symme…
GAIT: A Geometric Approach to Information Theory
Jose Gallego-Posada, Ankit Vani, Max Schwarzer +1
We advocate the use of a notion of entropy that reflects the relative abundances of the symbols in an alphabet, as well as the similarities between them. This concept was originall…
Beyond Local Nash Equilibria for Adversarial Networks
Frans A. Oliehoek, Rahul Savani, Jose Gallego +2
Save for some special cases, current training methods for Generative Adversarial Networks (GANs) are at best guaranteed to converge to a `local Nash equilibrium` (LNE). Such LNEs,…
GANGs: Generative Adversarial Network Games
Frans A. Oliehoek, Rahul Savani, Jose Gallego-Posada +3
Generative Adversarial Networks (GAN) have become one of the most successful frameworks for unsupervised generative modeling. As GANs are difficult to train much research has focus…