Search Results for author:
Found 14 papers, 4 papers with code
Addressing Sample Inefficiency in Multi-View Representation Learning
In this work, we provide theoretical insights on the implicit bias of the BarlowTwins and VICReg loss that can explain these heuristics and guide the development of more principled recommendations.
EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models
With the advent of deep learning application on edge devices, researchers actively try to optimize their deployments on low-power and restricted memory devices.
Score-based Denoising Diffusion with Non-Isotropic Gaussian Noise Models
Generative models based on denoising diffusion techniques have led to an unprecedented increase in the quality and diversity of imagery that is now possible to create with neural generative models.
A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods
In this work, we consider the Partial Domain Adaptation (PDA) variant, where we have extra source classes not present in the target domain.
On the Generalization of Representations in Reinforcement Learning
We complement our theoretical results with an empirical survey of classic representation learning methods from the literature and results on the Arcade Learning Environment, and find that the generalization behaviour of learned representations is well-explained by their effective dimension.
Multi-Resolution Continuous Normalizing Flows
In this work we introduce a Multi-Resolution variant of such models (MRCNF), by characterizing the conditional distribution over the additional information required to generate a fine image that is consistent with the coarse image.
Ranked #6 on
Image Generation
on ImageNet 64x64
(Bits per dim metric)
Frustratingly Easy Uncertainty Estimation for Distribution Shift
While the primary goal is to improve accuracy under distribution shift, an important secondary goal is uncertainty estimation: evaluating the probability that the prediction of a model is correct.
FairCal: Fairness Calibration for Face Verification
However, they still have drawbacks: they reduce accuracy (AGENDA, PASS, FTC), or require retuning for different false positive rates (FSN).
A principled approach for generating adversarial images under non-smooth dissimilarity metrics
This includes, but is not limited to, $\ell_1, \ell_2$, and $\ell_\infty$ perturbations; the $\ell_0$ counting "norm" (i. e. true sparseness); and the total variation seminorm, which is a (non-$\ell_p$) convolutional dissimilarity measuring local pixel changes.
Improved robustness to adversarial examples using Lipschitz regularization of the loss
We augment adversarial training (AT) with worst case adversarial training (WCAT) which improves adversarial robustness by 11% over the current state-of-the-art result in the $\ell_2$ norm on CIFAR-10.
Lipschitz regularized Deep Neural Networks generalize and are adversarially robust
In this work we study input gradient regularization of deep neural networks, and demonstrate that such regularization leads to generalization proofs and improved adversarial robustness.
Stochastic Backward Euler: An Implicit Gradient Descent Algorithm for $k$-means Clustering
In this paper, we propose an implicit gradient descent algorithm for the classic $k$-means problem.
Parle: parallelizing stochastic gradient descent
We propose a new algorithm called Parle for parallel training of deep networks that converges 2-4x faster than a data-parallel implementation of SGD, while achieving significantly improved error rates that are nearly state-of-the-art on several benchmarks including CIFAR-10 and CIFAR-100, without introducing any additional hyper-parameters.
Deep Relaxation: partial differential equations for optimizing deep neural networks
In this paper we establish a connection between non-convex optimization methods for training deep neural networks and nonlinear partial differential equations (PDEs).
