1 citations · 2 across the 10 of their papers we have counts for
7 papers · 1 filter
Gradient Prediction with Control Variates in the Cheap-Forward Regime
Kamil Ciosek, Nicolò Felicioni, Juan Elenter +1
We study whether otherwise-idle inference resources could reduce the scarce-GPU cost of training. Our analysis uses a simulated compute ledger in which fleet work is billed at a fr…
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…
LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning
Liangzu Peng, Juan Elenter, Joshua Agterberg +2
The goal of continual learning (CL) is to train a model that can solve multiple tasks presented sequentially. Recent CL approaches have achieved strong performance by leveraging la…
Near-Optimal Solutions of Constrained Learning Problems
Juan Elenter, Luiz F. O. Chamon, Alejandro Ribeiro
With the widespread adoption of machine learning systems, the need to curtail their behavior has become increasingly apparent. This is evidenced by recent advancements towards deve…
Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation
Juan Elenter, Navid NaderiAlizadeh, Tara Javidi +1
Continual learning is inherently a constrained learning problem. The goal is to learn a predictor under a no-forgetting requirement. Although several prior studies formulate it as…
Neural Networks with Quantization Constraints
Ignacio Hounie, Juan Elenter, Alejandro Ribeiro
Enabling low precision implementations of deep learning models, without considerable performance degradation, is necessary in resource and latency constrained settings. Moreover, e…
A Lagrangian Duality Approach to Active Learning
Juan Elenter, Navid NaderiAlizadeh, Alejandro Ribeiro
We consider the pool-based active learning problem, where only a subset of the training data is labeled, and the goal is to query a batch of unlabeled samples to be labeled so as t…