Keisuke Suzuki

Keisuke Suzuki

In this paper, we prove that an Adam-type algorithm with smooth clipping approaches the global minimizer of the regularized non-convex loss function. Adding smooth clipping and taking the state space as the set of all trajectories, we can apply the ergodic theory of Markov semigroups for this algorithm and investigate its asymptotic behavior. The ergodic theory we establish in this paper reduces the problem of evaluating the convergence, generalization error and discretization error of this algorithm to the problem of evaluating the difference between two functional stochastic differential equations (SDEs) with different drift coefficients. As a result of our analysis, we have shown that this algorithm minimizes the the regularized non-convex loss function with errors of the form $n^{-1/2}$, $η^{1/4}$, $β^{-1} \log (β+ 1)$ and $e^{- c t}$. Here, $c$ is a constant and $n$, $η$, $β$ and $t$ denote the size of the training dataset, learning rate, inverse temperature and time, respectively.

Keisuke Suzuki

In this paper, we propose a novel uniform generalization bound on the time and inverse temperature for stochastic gradient Langevin dynamics (SGLD) in a non-convex setting. While previous works derive their generalization bounds by uniform stability, we use Rademacher complexity to make our generalization bound independent of the time and inverse temperature. Using Rademacher complexity, we can reduce the problem to derive a generalization bound on the whole space to that on a bounded region and therefore can remove the effect of the time and inverse temperature from our generalization bound. As an application of our generalization bound, an evaluation on the effectiveness of the simulated annealing in a non-convex setting is also described. For the sample size $n$ and time $s$, we derive evaluations with orders $\sqrt{n^{-1} \log (n+1)}$ and $|(\log)^4(s)|^{-1}$, respectively. Here, $(\log)^4$ denotes the $4$ times composition of the logarithmic function.

Filippo Torresan, Keisuke Suzuki, Ryota Kanai et al.

Active inference is a formal approach to study cognition based on the notion that adaptive agents can be seen as engaging in a process of approximate Bayesian inference, via the minimisation of variational and expected free energies. Minimising the former provides an account of perceptual processes and learning as evidence accumulation, while minimising the latter describes how agents select their actions over time. In this way, adaptive agents are able to maximise the likelihood of preferred observations or states, given a generative model of the environment. In the literature, however, different strategies have been proposed to describe how agents can plan their future actions. While they all share the notion that some kind of expected free energy offers an appropriate way to score policies, sequences of actions, in terms of their desirability, there are different ways to consider the contribution of past motor experience to the agent's future behaviour. In some approaches, agents are assumed to know their own actions, and use such knowledge to better plan for the future. In other approaches, agents are unaware of their actions, and must infer their motor behaviour from recent observations in order to plan for the future. This difference reflects a standard point of departure in two leading frameworks in motor control based on the presence, or not, of an efference copy signal representing knowledge about an agent's own actions. In this work we compare the performances of action-aware and action-unaware agents in two navigations tasks, showing how action-unaware agents can achieve performances comparable to action-aware ones while at a severe disadvantage.