4 papers
Real World Time Series Benchmark Datasets with Distribution Shifts: Global Crude Oil Price and Volatility
Pranay Pasula
The scarcity of task-labeled time-series benchmarks in the financial domain hinders progress in continual learning. Addressing this deficit would foster innovation in this area. Th…
Mixture of basis for interpretable continual learning with distribution shifts
Mengda Xu, Sumitra Ganesh, Pranay Pasula
Continual learning in environments with shifting data distributions is a challenging problem with several real-world applications. In this paper we consider settings in which the d…
Lagrangian Duality in Reinforcement Learning
Pranay Pasula
Although duality is used extensively in certain fields, such as supervised learning in machine learning, it has been much less explored in others, such as reinforcement learning (R…
Complex Skill Acquisition Through Simple Skill Imitation Learning
Pranay Pasula
Humans often think of complex tasks as combinations of simpler subtasks in order to learn those complex tasks more efficiently. For example, a backflip could be considered a combin…