927 citations · 2.7k across the 88 of their papers we have counts for
7 papers · 1 filter
CrossSplit: Mitigating Label Noise Memorization through Data Splitting
Jihye Kim, Aristide Baratin, Yan Zhang +1
We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we prop…
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning
Sébastien Lachapelle, Tristan Deleu, Divyat Mahajan +4
Although disentangled representations are often said to be beneficial for downstream tasks, current empirical and theoretical understanding is limited. In this work, we provide evi…
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…
Partial Disentanglement via Mechanism Sparsity
Sébastien Lachapelle, Simon Lacoste-Julien
Disentanglement via mechanism sparsity was introduced recently as a principled approach to extract latent factors without supervision when the causal graph relating them in time is…
Dynamics of SGD with Stochastic Polyak Stepsizes: Truly Adaptive Variants and Convergence to Exact Solution
Antonio Orvieto, Simon Lacoste-Julien, Nicolas Loizou
Recently, Loizou et al. (2021), proposed and analyzed stochastic gradient descent (SGD) with stochastic Polyak stepsize (SPS). The proposed SPS comes with strong convergence guaran…
Data-Efficient Structured Pruning via Submodular Optimization
Marwa El Halabi, Suraj Srinivas, Simon Lacoste-Julien
Structured pruning is an effective approach for compressing large pre-trained neural networks without significantly affecting their performance. However, most current structured pr…
Bayesian Structure Learning with Generative Flow Networks
Tristan Deleu, António Góis, Chris Emezue +4
In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) structure of Bayesian networks, from data. Defining such a distr…