Automatic differentiation (AD) is conventionally understood as a family of distinct algorithms, rooted in two “modes”—forward and reverse—which are typically presented (and implemented) separately. Can there be only one? Following up on the AD systems developed in the JAX and Dex projects, we formalize a decomposition of reverse-mode AD into (i) forward-mode AD followed by (ii) unzipping the linear and non-linear parts and then (iii) transposition of the linear part. To that end, we define a (substructurally) linear type system that can prove a class of functions are (algebraically) linear. Our main results are that forward-mode AD produces such linear functions, and that we can unzip and transpose any such linear function, conserving cost, size, and linearity. Composing these three transformations recovers reverse-mode AD. This decomposition also sheds light on checkpointing, which emerges naturally from a free choice in unzipping let expressions. As a corollary, checkpointing techniques are applicable to general-purpose partial evaluation, not just AD. We hope that our formalization will lead to a deeper understanding of automatic differentiation and that it will simplify implementations, by separating the concerns of differentiation proper from the concerns of gaining efficiency (namely, separating the derivative computation from the act of running it backward).

Hamiltonian Monte Carlo (HMC) is a powerful MCMC algorithm based on simulating Hamiltonian dynamics. Its performance depends strongly on choosing appropriate values for two parameters: the step size used in the simulation, and how long the simulation runs for. The step-size parameter can be tuned using standard adaptive-MCMC strategies, but it is less obvious how to tune the simulation-length parameter. The no-U-turn sampler (NUTS) eliminates this problematic simulation-length parameter, but NUTS’s relatively complex control flow makes it difficult to efficiently run many parallel chains on accelerators such as GPUs. NUTS also spends some extra gradient evaluations relative to HMC in order to decide how long to run each iteration without violating detailed balance. We propose ChEES-HMC, a simple adaptive-MCMC scheme for automatically tuning HMC’s simulation-length parameter, which minimizes a proxy for the autocorrelation of the state’s second moments. We evaluate ChEES-HMC and NUTS on many tasks, and find that ChEES-HMC typically yields larger effective sample sizes per gradient evaluation than NUTS does. When running many chains on a GPU, ChEES-HMC can also run significantly more gradient evaluations per second than NUTS, allowing it to quickly provide accurate estimates of posterior expectations.

Probabilistic programming systems generally compute with probability density functions, leaving the base measure of each such function implicit. This mostly works, but creates problems when densities with respect to different base measures are accidentally combined or compared. Mistakes also happen when computing volume corrections for continuous changes of variables, which in general depend on the support measure. We motivate and clarify the problem in the context of a composable library of probability distributions and bijective transformations. We solve the problem by standardizing on Hausdorff measure as a base, and deriving formulas for comparing and combining mixed-dimension densities, as well as updating densities with respect to Hausdorff measure under diffeomorphic transformations. We also propose a software architecture that implements these formulas efficiently in the common case. We hope that by adopting our solution, probabilistic programming systems can become more robust and general, and make a broader class of models accessible to practitioners.

We present a novel programming language design that attempts to combine the clarity and safety of high-level functional languages with the efficiency and parallelism of low-level numerical languages. We treat arrays as eagerly-memoized functions on typed index sets, allowing abstract function manipulations, such as currying, to work on arrays. In contrast to composing primitive bulk-array operations, we argue for an explicit nested indexing style that mirrors application of functions to arguments. We also introduce a fine-grained typed effects system which affords concise and automatically-parallelized in-place updates. Specifically, an associative accumulation effect allows reverse-mode automatic differentiation of in-place updates in a way that preserves parallelism. Empirically, we benchmark against the Futhark array programming language, and demonstrate that aggressive inlining and type-driven compilation allows array programs to be written in an expressive, "pointful" style with little performance penalty.

Abstract Automatic differentiation (AD) is a technique for augmenting computer programs to compute derivatives. The essence of AD in its forward accumulation mode is to attach perturbations to each number, and propagate these through the computation by overloading the arithmetic operators. When derivatives are nested, the distinct derivative calculations, and their associated perturbations, must be distinguished. This is typically accomplished by creating a unique tag for each derivative calculation and tagging the perturbations. We exhibit a subtle bug, present in fielded implementations which support derivatives of higher-order functions, in which perturbations are confused despite the tagging machinery, leading to incorrect results. The essence of the bug is as follows: a unique tag is needed for each derivative calculation, but in existing implementations unique tags are created when taking the derivative of a function at a point. When taking derivatives of higher-order functions, these need not correspond! We exhibit a simple example: a higher-order function f whose derivative at a point x , namely f ′( x ), is itself a function which calculates a derivative. This situation arises naturally when taking derivatives of curried functions. Two potential solutions are presented, and their deficiencies discussed. One uses eta expansion to delay the creation of fresh tags in order to put them into one-to-one correspondence with derivative calculations. The other wraps outputs of derivative operators with tag substitution machinery. Both solutions seem very difficult to implement without violating the desirable complexity guarantees of forward AD.

We describe a simple, low-level approach for embedding probabilistic programming in a deep learning ecosystem. In particular, we distill probabilistic programming down to a single abstraction—the random variable. Our lightweight implementation in TensorFlow enables numerous applications: a model-parallel variational auto-encoder (VAE) with 2nd-generation tensor processing units (TPUv2s); a data-parallel autoregressive model (Image Transformer) with TPUv2s; and multi-GPU No-U-Turn Sampler (NUTS). For both a state-of-the-art VAE on 64x64 ImageNet and Image Transformer on 256x256 CelebA-HQ, our approach achieves an optimal linear speedup from 1 to 256 TPUv2 chips. With NUTS, we see a 100x speedup on GPUs over Stan and 37x over PyMC3.

We introduce inference metaprogramming for probabilistic programming languages, including new language constructs, a formalism, and the rst demonstration of e ectiveness in practice. Instead of relying on rigid black-box inference algorithms hard-coded into the language implementation as in previous probabilistic programming languages, infer- ence metaprogramming enables developers to 1) dynamically decompose inference problems into subproblems, 2) apply in- ference tactics to subproblems, 3) alternate between incorpo- rating new data and performing inference over existing data, and 4) explore multiple execution traces of the probabilis- tic program at once. Implemented tactics include gradient- based optimization, Markov chain Monte Carlo, variational inference, and sequental Monte Carlo techniques. Inference metaprogramming enables the concise expression of proba- bilistic models and inference algorithms across diverse elds, such as computer vision, data science, and robotics, within a single probabilistic programming language.

Reasoning with probabilistic models is a widespread and successful technique in areas ranging from computer vision, to natural language processing, to bioinformatics. Currently, these reasoning systems are either coded from scratch in general-purpose languages or use formalisms such as Bayesian networks that have limited expressive power. In both cases, the resulting systems are difficult to modify, maintain, compose, and interoperate with. This work presents Probabilistic Scheme, an embedding of probabilistic computation into Scheme. This gives programmers an expressive language for implementing modular probabilistic models that integrate naturally with the rest of Scheme.