AI Evening @SGInnovate
Join us to learn about large-scale hyper parameter tuning using automatic differentiation instead of bayesian optimisation, as well as how to use Deep Reinforcement Learning for financial trading!
Large-scale Automatic Hyperparameter Tuning for Deep Learning – Jie Fu, NUS PHD (2017)
Jie Fu will be sharing on DrMAD.
DrMAD is a hyperparameter tuning method based on automatic differentiation, which is an underused tool for machine learning. DrMAD can tune thousands of continuous hyperparameters (e.g. L1 norms for every single neuron) for deep models on GPUs.
Deep Reinforcement Learning for Optimal Order Placement in a Limit Order Book (Quantitative Finance) – IIija Ilievski, NUS PHD Candidate
Financial trading is essentially a search problem. The buy-side agent must find a counterpart sell-side agent willing to trade the financial asset at the set quantity and price. The virtual space where the agents execute their trading actions is called limit-order book. We present a deep reinforcement learning algorithm for optimizing the execution of limit-order actions to find an optimal order placement. The reinforcement learning agent utilizes historical limit-order data to learn an optimal compromise between fast order completion but with higher costs and slow, riskier order completion but with lower costs. We also give a technological overview of the system and discuss the challenges and potential future work.