Search Results for author:
Found 18 papers, 8 papers with code
On Inference Stability for Diffusion Models
To minimize that gap, we propose a novel \textit{sequence-aware} loss that aims to reduce the estimation gap to enhance the sampling quality.
KOPPA: Improving Prompt-based Continual Learning with Key-Query Orthogonal Projection and Prototype-based One-Versus-All
Drawing inspiration from prompt tuning techniques applied to Large Language Models, recent methods based on pre-trained ViT networks have achieved remarkable results in the field of Continual Learning.
Robust Contrastive Learning With Theory Guarantee
Contrastive learning (CL) is a self-supervised training paradigm that allows us to extract meaningful features without any label information.
SigFormer: Signature Transformers for Deep Hedging
To mitigate such difficulties, we introduce SigFormer, a novel deep learning model that combines the power of path signatures and transformers to handle sequential data, particularly in cases with irregularities.
Conditional Support Alignment for Domain Adaptation with Label Shift
In this paper, we propose a novel conditional adversarial support alignment (CASA) whose aim is to minimize the conditional symmetric support divergence between the source's and target domain's feature representation distributions, aiming at a more helpful representation for the classification task.
Reducing Training Time in Cross-Silo Federated Learning using Multigraph Topology
In this paper, we present a new multigraph topology for cross-silo federated learning.
Stochastic Multiple Target Sampling Gradient Descent
Furthermore, when analysing its asymptotic properties, SVGD reduces exactly to a single-objective optimization problem and can be viewed as a probabilistic version of this single-objective optimization problem.
Distributionally Robust Fair Principal Components via Geodesic Descents
Principal component analysis is a simple yet useful dimensionality reduction technique in modern machine learning pipelines.
On Learning Domain-Invariant Representations for Transfer Learning with Multiple Sources
Domain adaptation (DA) benefits from the rigorous theoretical works that study its insightful characteristics and various aspects, e. g., learning domain-invariant representations and its trade-off.
Exploiting Domain-Specific Features to Enhance Domain Generalization
We empirically show that mDSDI provides competitive results with state-of-the-art techniques in DG.
LASSO: Latent Sub-spaces Orientation for Domain Generalization
To achieve a satisfactory generalization performance on prediction tasks in an unseen domain, existing domain generalization (DG) approaches often rely on the strict assumption of fixed domain-invariant features and common hypotheses learned from a set of training domains.
KL Guided Domain Adaptation
A common approach in the domain adaptation literature is to learn a representation of the input that has the same (marginal) distribution over the source and the target domain.
Domain Invariant Representation Learning with Domain Density Transformations
Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains.
Bayesian Metric Learning for Robust Training of Deep Models under Noisy Labels
Label noise is a natural event of data collection and annotation and has been shown to have significant impact on the performance of deep learning models regarding accuracy reduction and sample complexity increase.
Learning Compositional Sparse Gaussian Processes with a Shrinkage Prior
Choosing a proper set of kernel functions is an important problem in learning Gaussian Process (GP) models since each kernel structure has different model complexity and data fitness.
Bayesian Generative Active Deep Learning
Deep learning models have demonstrated outstanding performance in several problems, but their training process tends to require immense amounts of computational and human resources for training and labeling, constraining the types of problems that can be tackled.
A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning
Another approach explored in the field relies on an ad-hoc linearization (in terms of N) of the triplet loss that introduces class centroids, which must be optimized using the whole training set for each mini-batch - this means that a naive implementation of this approach has run-time complexity O(N^2).
A Bayesian Data Augmentation Approach for Learning Deep Models
Data augmentation is an essential part of the training process applied to deep learning models.
