Even Initialization
In this paper, we propose a new weight initialization method called even initialization for wide and deep nonlinear neural networks with the ReLU activation function. We prove that no poor local minimum exists in the initial loss landscape in the wide and deep nonlinear neural network initialized by the even initialization method that we propose. Specifically, in the initial loss landscape of such a wide and deep ReLU neural network model, the following four statements hold true: 1) the loss function is non-convex and non-concave; 2) every local minimum is a global minimum; 3) every critical point that is not a global minimum is a saddle point; and 4) bad saddle points exist. We also show that the weight values initialized by the even initialization method are contained in those initialized by both of the (often used) standard initialization and He initialization methods. …

Wallaroo
Wallaroo is a fast, elastic data processing engine that rapidly takes you from prototype to production by eliminating infrastructure complexity. Wallaroo is a fast and elastic data processing engine that rapidly takes you from prototype to production by making the infrastructure virtually disappear. We´ve designed it to handle demanding high-throughput, low-latency tasks where the accuracy of results is essential. Wallaroo takes care of mechanics of scaling, resilience, state management, and message delivery. We’ve designed Wallaroo to make it easy scale applications with no code changes, and allow programmers to focus on business logic. …

VIREL
Applying probabilistic models to reinforcement learning (RL) has become an exciting direction of research owing to powerful optimisation tools such as variational inference becoming applicable to RL. However, due to their formulation, existing inference frameworks and their algorithms pose significant challenges for learning optimal policies, for example, the absence of mode capturing behaviour in pseudo-likelihood methods and difficulties in optimisation of learning objective in maximum entropy RL based approaches. We propose VIREL, a novel, theoretically grounded probabilistic inference framework for RL that utilises the action-value function in a parametrised form to capture future dynamics of the underlying Markov decision process. Owing to it’s generality, our framework lends itself to current advances in variational inference. Applying the variational expectation-maximisation algorithm to our framework, we show that actor-critic algorithm can be reduced to expectation-maximization. We derive a family of methods from our framework, including state-of-the-art methods based on soft value functions. We evaluate two actor-critic algorithms derived from this family, which perform on par with soft actor critic, demonstrating that our framework offers a promising perspective on RL as inference. …

Maximum Expected Utility
Principle of maximum expected utility: A rational agent should chose the action which maximizes ist expected utility, given its knowledge.
➚ “Expected Utility Hypothesis” …