Ürün Doǧan
YOU?
Author Swipe
View article: Value bounds and Convergence Analysis for Averages of LRP attributions
Value bounds and Convergence Analysis for Averages of LRP attributions Open
We analyze numerical properties of Layer-wise relevance propagation (LRP)-type attribution methods by representing them as a product of modified gradient matrices. This representation creates an analogy to matrix multiplications of Jacobi-…
View article: Pearl: A Production-ready Reinforcement Learning Agent
Pearl: A Production-ready Reinforcement Learning Agent Open
Reinforcement learning (RL) is a versatile framework for optimizing long-term goals. Although many real-world problems can be formalized with RL, learning and deploying a performant RL policy requires a system designed to address several i…
View article: IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control
IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control Open
Model-based reinforcement learning (RL) has shown great promise due to its sample efficiency, but still struggles with long-horizon sparse-reward tasks, especially in offline settings where the agent learns from a fixed dataset. We hypothe…
View article: Representation learning for clustering via building consensus
Representation learning for clustering via building consensus Open
In this paper, we focus on unsupervised representation learning for clustering of images. Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated t…
View article: Offline RL With Resource Constrained Online Deployment
Offline RL With Resource Constrained Online Deployment Open
Offline reinforcement learning is used to train policies in scenarios where real-time access to the environment is expensive or impossible. As a natural consequence of these harsh conditions, an agent may lack the resources to fully observ…
View article: Consensus Clustering With Unsupervised Representation Learning
Consensus Clustering With Unsupervised Representation Learning Open
Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated through data augmentation techniques) must either be closer in the representation space, or…
View article: Representation Learning for Clustering via Building Consensus
Representation Learning for Clustering via Building Consensus Open
In this paper, we focus on unsupervised representation learning for clustering of images. Recent advances in deep clustering and unsupervised representation learning are based on the idea that different views of an input image (generated t…
View article: Zero Shot Domain Generalization
Zero Shot Domain Generalization Open
Standard supervised learning setting assumes that training data and test data come from the same distribution (domain). Domain generalization (DG) methods try to learn a model that when trained on data from multiple domains, would generali…
View article: Self-Supervised Contextual Bandits in Computer Vision
Self-Supervised Contextual Bandits in Computer Vision Open
Contextual bandits are a common problem faced by machine learning practitioners in domains as diverse as hypothesis testing to product recommendations. There have been a lot of approaches in exploiting rich data representations for context…
View article: Data Transformation Insights in Self-supervision with Clustering Tasks
Data Transformation Insights in Self-supervision with Clustering Tasks Open
Self-supervision is key to extending use of deep learning for label scarce domains. For most of self-supervised approaches data transformations play an important role. However, up until now the impact of transformations have not been studi…
View article: A Generalization Error Bound for Multi-class Domain Generalization
A Generalization Error Bound for Multi-class Domain Generalization Open
Domain generalization is the problem of assigning labels to an unlabeled data set, given several similar data sets for which labels have been provided. Despite considerable interest in this problem over the last decade, there has been no t…
View article: Domain Generalization by Marginal Transfer Learning
Domain Generalization by Marginal Transfer Learning Open
In the problem of domain generalization (DG), there are labeled training data sets from several related prediction problems, and the goal is to make accurate predictions on future unlabeled data sets that are not known to the learner. This…
View article: Data-dependent Generalization Bounds for Multi-class Classification
Data-dependent Generalization Bounds for Multi-class Classification Open
In this paper, we study data-dependent generalization error bounds exhibiting a mild dependency on the number of classes, making them suitable for multi-class learning with a large number of label classes. The bounds generally hold for emp…
View article: Distributed optimization of multi-class SVMs
Distributed optimization of multi-class SVMs Open
Training of one-vs.-rest SVMs can be parallelized over the number of classes in a straight forward way. Given enough computational resources, one-vs.-rest SVMs can thus be trained on data involving a large number of classes. The same canno…
View article: Multi-Task Learning for Contextual Bandits
Multi-Task Learning for Contextual Bandits Open
Contextual bandits are a form of multi-armed bandit in which the agent has access to predictive side information (known as the context) for each arm at each time step, and have been used to model personalized news recommendation, ad placem…
View article: Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to\n Novel Algorithms
Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to\n Novel Algorithms Open
This paper studies the generalization performance of multi-class\nclassification algorithms, for which we obtain, for the first time, a\ndata-dependent generalization error bound with a logarithmic dependence on the\nclass size, substantia…
View article: Localized Multiple Kernel Learning---A Convex Approach
Localized Multiple Kernel Learning---A Convex Approach Open
We propose a localized approach to multiple kernel learning that can be formulated as a convex optimization problem over a given cluster structure. For which we obtain generalization error guarantees and derive an optimization algorithm ba…
View article: Localized Multiple Kernel Learning---A Convex Approach
Localized Multiple Kernel Learning---A Convex Approach Open
We propose a localized approach to multiple kernel learning that can be formulated as a convex optimization problem over a given cluster structure. For which we obtain generalization error guarantees and derive an optimization algorithm ba…
View article: Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms
Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms Open
This paper studies the generalization performance of multi-class classification algorithms, for which we obtain, for the first time, a data-dependent generalization error bound with a logarithmic dependence on the class size, substantially…