Diego Klabjan

Open-Set Recognition with Gaussian Mixture Variational Autoencoders

2020 · arXiv (Cornell University)

In inference, open-set classification is to either classify a sample into a known class from training or reject it as an unknown class. Existing deep open-set classifiers train explicit closed-set classifiers, in some cases disjointly …

Divergence Results and Convergence of a Variance Reduced Version of ADAM

2022 · arXiv (Cornell University)

Stochastic optimization algorithms using exponential moving averages of the past gradients, such as ADAM, RMSProp and AdaGrad, have been having great successes in many applications, especially in training deep neural networks. ADAM in particular stands …

Early Classifying Multimodal Sequences

2023 · arXiv (Cornell University)

Often pieces of information are received sequentially over time. When did one collect enough such pieces to classify? Trading wait time for decision certainty leads to early classification problems that have recently gained attention as …

On the Second-Order Convergence of Biased Policy Gradient Algorithms

2023 · arXiv (Cornell University)

Since the objective functions of reinforcement learning problems are typically highly nonconvex, it is desirable that policy gradient, the most popular algorithm, escapes saddle points and arrives at second-order stationary points. Existing results only consider …