Deep RL is hot these days. It’s one of the most popular topics in the submissions at NeurIPS / ICLR / ICML and other ML conferences. And while the definition of RL is pretty general, in this note I’d argue that the famous REINFORCE algorithm alone is not enough to label your method as a Reinforcement Learning one.
I have been looking at \(f\)-GANs derivation doing some of my research, and found an easier way to derive its lower bound, without invoking convex conjugate functions.
This posts finishes the discussion started in the Thoughts on Mutual Information: More Estimators with a consideration of alternatives to the Mutual Information.
This posts continues the discussion started in the Thoughts on Mutual Information: More Estimators. This time we’ll focus on drawbacks and limitations of these bounds.
In this post I’d like to show how Self-Normalized Importance Sampling (IWHVI and IWAE) and Annealed Importance Sampling can be used to give (sometimes sandwich) bounds on the MI in many different cases.
This post finishes the discussion on Neural Samplers for Variational Inference by introducing some recent results (including mine).
Also, there’s a talk recording of me presenting this post’s content, so if you like videos more than texts, check it out.
This post sets background for the upcoming post on my work on more efficient use of neural samplers for Variational Inference.
This is the final post of the stochastic computation graphs series. Last time we discussed models with discrete relaxations of stochastic nodes, which allowed us to employ the power of reparametrization.
These methods, however, posses one flaw: they consider different models, thus introducing inherent bias – your test time discrete model will be doing something different from what your training time model did. Therefore in this post we’ll get back to the REINFORCE aka Score Function estimator, and see if we can fix its problems.
This is the second post of the stochastic computation graphs series. Last time we discussed models with continuous stochastic nodes, for which there are powerful reparametrization technics.
Unfortunately, these methods don’t work for discrete random variables. Moreover, it looks like there’s no way to backpropagate through discrete stochastic nodes, as there’s no infinitesimal change of random values when you infinitesimally perturb their parameters.
In this post I’ll talk about continuous relaxations of discrete random variables.
Last year I covered some modern Variational Inference theory. These methods are often used in conjunction with Deep Neural Networks to form deep generative models (VAE, for example) or to enrich deterministic models with stochastic control, which leads to better exploration. Or you might be interested in amortized inference.
All these cases turn your computation graph into a stochastic one – previously deterministic nodes now become random. And it’s not obvious how to do backpropagation through these nodes. In this series I’d like to outline possible approaches. This time we’re going to see why general approach works poorly, and see what we can do in a continuous case.
Just like with NIPS last year, here’s a list of ICML’17 summaries (updated as I stumble upon new ones)
The more I talk to people online, the more I hear about the famous No Free Lunch Theorem (NFL theorem). Unfortunately, quite often people don’t really understand what the theorem is about, and what its implications are. In this post I’d like to share my view on the NFL theorem, and some other impossibility results.
I did not attend this year’s NIPS, but I’ve gathered many summaries published online by those who did attend the conference.
Previously we covered Variational Autoencoders (VAE) — popular inference tool based on neural networks. In this post we’ll consider, a followup work from Torronto by Y. Burda, R. Grosse and R. Salakhutdinov, Importance Weighted Autoencoders (IWAE). The crucial contribution of this work is introduction of a new lower-bound on the marginal log-likelihood \(\log p(x)\) which generalizes ELBO, but also allows one to use less accurate approximate posteriors \(q(z \mid x, \Lambda)\).
On a dessert we’ll discuss another paper, Variational inference for Monte Carlo objectives by A. Mnih and D. Rezende which aims to broaden the applicability of this approach to models where reparametrization trick can not be used (e.g. for discrete variables).
So far we had a little of “neural” in our VI methods. Now it’s time to fix it, as we’re going to consider Variational Autoencoders (VAE), a paper by D. Kingma and M. Welling, which made a lot of buzz in ML community. It has 2 main contributions: a new approach (AEVB) to large-scale inference in non-conjugate models with continuous latent variables, and a probabilistic model of autoencoders as an example of this approach. We then discuss connections to Helmholtz machines — a predecessor of VAEs.
In the previous post we covered Stochastic VI: an efficient and scalable variational inference method for exponential family models. However, there’re many more distributions than those belonging to the exponential family. Inference in these cases requires significant amount of model analysis. In this post we consider Black Box Variational Inference by Ranganath et al. This work just as the previous one comes from David Blei lab — one of the leading researchers in VI. And, just for the dessert, we’ll touch upon another paper, which will finally introduce some neural networks in VI.
In the previous post I covered well-established classical theory developed in early 2000-s. Since then technology has made huge progress: now we have much more data, and a great need to process it and process it fast. In big data era we have huge datasets, and can not afford too many full passes over it, which might render classical VI methods impractical. Recently M. Hoffman et al. dissected classical Mean-Field VI to introduce stochasticity right into its heart, which resulted in Stochastic Variational Inference.
As a member of Bayesian methods research group I’m heavily interested in Bayesian approach to machine learning. One of the strengths of this approach is ability to work with hidden (unobserved) variables which are interpretable. This power however comes at a cost of generally intractable exact inference, which limits the scope of solvable problems.
Another topic which gained lots of momentum in Machine Learning recently is Deep Learning, of course. With Deep Learning we can now build big and complex models that outperform most hand-engineered approaches given lots of data and computational power. The fact that Deep Learning needs a considerable amount of data also requires these methods to be scalable — a really nice property for any algorithm to have, especially in a Big Data epoch.
Given how appealing both topics are it’s not a surprise there’s been some work to marry these two recently. In this series of blogsposts I’d like to summarize recent advances, particularly in variational inference. This is not meant to be an introductory discussion as prior familiarity with classical topics (Latent variable models, Variational Inference, Mean-field approximation) is required, though I’ll introduce these ideas anyway just to remind it and setup the notation.