Search

Context: Edge graphs are graphs whose edges are labelled with identifiers, and nodes can have multiple edges between them. They are used to model a wide range of systems, including networks with distances or degrees of connection and complex relational data. Inquiry: Unfortunately, the homogeneity of this graph structure prevents an effective representation in (functional) programs. Either their interface is riddled with partial functions, or the representations are computationally inefficient to process. Approach: We present a novel data type for edge graphs, based on total and recursive definitions, that prevents usage errors from partial APIs and promotes structurally recursive computations. We follow an algebraic approach and provide a set of primitive constructors and combinators, along with equational laws that identify semantically equivalent constructions. Knowledge: This algebra translates directly into an implementation using algebraic data types, and its homomorphisms give rise to functions for manipulating and transforming these edge graphs. Grounding: We exploit the fact that many common graph algorithms are such homomorphisms to implement them in our framework. Importance: In giving a theoretical grounding for the edge graph data type, we can formalise properties such as soundness and completeness of the representation while also minimising usage errors and maximising re-usability.

Bipartite Experiments are randomized experiments where the treatment is applied to a set of units (randomization units) that is different from the units of analysis, and randomization units and analysis units are connected through a bipartite graph. The scale of experimentation at large online platforms necessitates both accurate inference in the presence of a large bipartite interference graph, as well as a highly scalable implementation. In this paper, we describe new methods for inference that enable practical, scalable analysis of bipartite experiments: (1) We propose CA-ERL, a covariate-adjusted variant of the exposure-reweighted-linear (ERL) estimator [9], which empirically yields 60-90% variance reduction. (2) We introduce a randomization-based method for inference and prove asymptotic validity of a Wald-type confidence interval under graph sparsity assumptions. (3) We present a linear-time algorithm for randomization inference of the CA-ERL estimator, which can be easily implemented in query engines like Presto or Spark. We evaluate our methods both on a real experiment at Meta that randomized treatment on Facebook Groups and analyzed user-level metrics, as well as simulations on synthetic data. The real-world data shows that our CA-ERL estimator reduces the confidence interval (CI) width by 60-90% (compared to ERL) in a practical setting. The simulations using synthetic data show that our randomization inference procedure achieves correct coverage across instances, while the ERL estimator has incorrectly small CI widths for instances with large true effect sizes and is overly conservative when the bipartite graph is dense.

Online A/B testing is widely used in the internet industry to inform decisions on new feature roll-outs. For online marketplaces (such as advertising markets), standard approaches to A/B testing may lead to biased results when buyers operate under a budget constraint, as budget consumption in one arm of the experiment impacts performance of the other arm. To counteract this interference, one can use a budget-split design where the budget constraint operates on a per-arm basis and each arm receives an equal fraction of the budget, leading to ``budget-controlled A/B testing.'' Despite clear advantages of budget-controlled A/B testing, performance degrades when budget are split too small, limiting the overall throughput of such systems. In this paper, we propose a parallel budget-controlled A/B testing design where we use market segmentation to identify submarkets in the larger market, and we run parallel experiments on each submarket. Our contributions are as follows: First, we introduce and demonstrate the effectiveness of the parallel budget-controlled A/B test design with submarkets in a large online marketplace environment. Second, we formally define market interference in first-price auction markets using the first price pacing equilibrium (FPPE) framework. Third, we propose a debiased surrogate that eliminates the first-order bias of FPPE, drawing upon the principles of sensitivity analysis in mathematical programs. Fourth, we derive a plug-in estimator for the surrogate and establish its asymptotic normality. Fifth, we provide an estimation procedure for submarket parallel budget-controlled A/B tests. Finally, we present numerical examples on semi-synthetic data, confirming that the debiasing technique achieves the desired coverage properties.

Some effects are considered to be higher-level than others. High-level effects provide expressive and succinct abstraction of programming concepts, while low-level effects allow more fine-grained control over program execution and resources. Yet, often it is desirable to write programs using the convenient abstraction offered by high-level effects, and meanwhile still benefit from the optimisations enabled by low-level effects. One solution is to translate high-level effects to low-level ones. This paper studies how algebraic effects and handlers allow us to simulate high-level effects in terms of low-level effects. In particular, we focus on the interaction between state and nondeterminism known as the local state, as provided by Prolog. We map this high-level semantics in successive steps onto a low-level composite state effect, similar to that managed by Prolog's Warren Abstract Machine. We first give a translation from the high-level local-state semantics to the low-level global-state semantics, by explicitly restoring state updates on backtracking. Next, we eliminate nondeterminsm altogether in favor of a lower-level state containing a choicepoint stack. Then we avoid copying the state by restricting ourselves to incremental, reversible state updates. We show how these updates can be stored on a trail stack with another state effect. We prove the correctness of all our steps using program calculation where the fusion laws of effect handlers play a central role., Comment: 120 pages

This paper studies the design of cluster experiments to estimate the global treatment effect in the presence of network spillovers. We provide a framework to choose the clustering that minimizes the worst-case mean-squared error of the estimated global effect. We show that optimal clustering solves a novel penalized min-cut optimization problem computed via off-the-shelf semi-definite programming algorithms. Our analysis also characterizes simple conditions to choose between any two cluster designs, including choosing between a cluster or individual-level randomization. We illustrate the method's properties using unique network data from the universe of Facebook's users and existing data from a field experiment.

In online advertising markets, budget-constrained advertisers acquire ad placements through repeated bidding in auctions on various platforms. We present a strategy for bidding optimally in a set of auctions that may or may not be incentive-compatible under the presence of budget constraints. Our strategy maximizes the expected total utility across auctions while satisfying the advertiser's budget constraints in expectation. Additionally, we investigate the online setting where the advertiser must submit bids across platforms while learning about other bidders' bids over time. Our algorithm has $O(T^{3/4})$ regret under the full-information setting. Finally, we demonstrate that our algorithms have superior cumulative regret on both synthetic and real-world datasets of ad placement auctions, compared to existing adaptive pacing algorithms., Comment: 34 pages, 5 figures

Automatic differentiation (AD) is a range of algorithms to compute the numeric value of a function's (partial) derivative, where the function is typically given as a computer program or abstract syntax tree. AD has become immensely popular as part of many learning algorithms, notably for neural networks. This paper uses Prolog to systematically derive gradient-based forward- and reverse-mode AD variants from a simple executable specification: evaluation of the symbolic derivative. Along the way we demonstrate that several Prolog features (DCGs, co-routines) contribute to the succinct formulation of the algorithm. We also discuss two applications in probabilistic programming that are enabled by our Prolog algorithms. The first is parameter learning for the Sum-Product Loop Language and the second consists of both parameter learning and variational inference for probabilistic logic programming., Comment: accepted for publication in the issues of Theory and Practice of Logic Programming dedicated to ICLP 2023

Algebraic effects & handlers have become a standard approach for side-effects in functional programming. Their modular composition with other effects and clean separation of syntax and semantics make them attractive to a wide audience. However, not all effects can be classified as algebraic; some need a more sophisticated handling. In particular, effects that have or create a delimited scope need special care, as their continuation consists of two parts-in and out of the scope-and their modular composition introduces additional complexity. These effects are called scoped and have gained attention by their growing applicability and adoption in popular libraries. While calculi have been designed with algebraic effects & handlers built in to facilitate their use, a calculus that supports scoped effects & handlers in a similar manner does not yet exist. This work fills this gap: we present $\lambda_{\mathit{sc}}$, a calculus with native support for both algebraic and scoped effects & handlers. It addresses the need for polymorphic handlers and explicit clauses for forwarding unknown scoped operations to other handlers. Our calculus is based on Eff, an existing calculus for algebraic effects, extended with Koka-style row polymorphism, and consists of a formal grammar, operational semantics, a (type-safe) type-and-effect system and type inference. We demonstrate $\lambda_{\mathit{sc}}$ on a range of examples.

Algebraic effects & handlers are a modular approach for modeling side-effects in functional programming. Their syntax is defined in terms of a signature of effectful operations, encoded as a functor, that are plugged into the free monad; their denotational semantics is defined by fold-style handlers that only interpret their part of the syntax and forward the rest. However, not all effects are algebraic: some need to access an internal computation. For example, scoped effects distinguish between a computation in scope and out of scope; parallel effects parallellize over a computation, latent effects defer a computation. Separate definitions have been proposed for these higher-order effects and their corresponding handlers, often leading to expedient and complex monad definitions. In this work we propose a generic framework for higher-order effects, generalizing algebraic effects & handlers: a generic free monad with higher-order effect signatures and a corresponding interpreter. Specializing this higher-order syntax leads to various definitions of previously defined (scoped, parallel, latent) and novel (writer, bracketing) effects. Furthermore, we formally show our framework theoretically correct, also putting different effect instances on formal footing; a significant contribution for parallel, latent, writer and bracketing effects.

Automatic differentiation (AD) has been a topic of interest for researchers in many disciplines, with increased popularity since its application to machine learning and neural networks. Although many researchers appreciate and know how to apply AD, it remains a challenge to truly understand the underlying processes. From an algebraic point of view, however, AD appears surprisingly natural: it originates from the differentiation laws. In this work we use Algebra of Programming techniques to reason about different AD variants, leveraging Haskell to illustrate our observations. Our findings stem from three fundamental algebraic abstractions: (1) the notion of module over a semiring, (2) Nagata's construction of the 'idealization of a module', and (3) Kronecker's delta function, that together allow us to write a single-line abstract definition of AD. From this single-line definition, and by instantiating our algebraic structures in various ways, we derive different AD variants, that have the same extensional behaviour, but different intensional properties, mainly in terms of (asymptotic) computational complexity. We show the different variants equivalent by means of Kronecker isomorphisms, a further elaboration of our Haskell infrastructure which guarantees correctness by construction. With this framework in place, this paper seeks to make AD variants more comprehensible, taking an algebraic perspective on the matter.

GitHub hosts hundreds of millions of code repositories written in hundreds of different programming languages. In addition to its hosting services, GitHub provides data and insights into code, such as vulnerability analysis and code navigation, with which users can improve and understand their software development process. GitHub has built Semantic, a program analysis tool capable of parsing and extracting detailed information from source code. The development of Semantic has relied extensively on the functional programming literature; this paper describes how connections to academic research inspired and informed the development of an industrial-scale program analysis toolkit., Comment: 14 pages, 2 figures, submitted to ICFP 2022

In this data release from the LOFAR Two-metre Sky Survey (LoTSS) we present 120-168MHz images covering 27% of the northern sky. Our coverage is split into two regions centred at approximately 12h45m +44$^\circ$30' and 1h00m +28$^\circ$00' and spanning 4178 and 1457 square degrees respectively. The images were derived from 3,451hrs (7.6PB) of LOFAR High Band Antenna data which were corrected for the direction-independent instrumental properties as well as direction-dependent ionospheric distortions during extensive, but fully automated, data processing. A catalogue of 4,396,228 radio sources is derived from our total intensity (Stokes I) maps, where the majority of these have never been detected at radio wavelengths before. At 6" resolution, our full bandwidth Stokes I continuum maps with a central frequency of 144MHz have: a median rms sensitivity of 83$\mu$Jy/beam; a flux density scale accuracy of approximately 10%; an astrometric accuracy of 0.2"; and we estimate the point-source completeness to be 90% at a peak brightness of 0.8mJy/beam. By creating three 16MHz bandwidth images across the band we are able to measure the in-band spectral index of many sources, albeit with an error on the derived spectral index of +/-0.2 which is a consequence of our flux-density scale accuracy and small fractional bandwidth. Our circular polarisation (Stokes V) 20" resolution 120-168MHz continuum images have a median rms sensitivity of 95$\mu$Jy/beam, and we estimate a Stokes I to Stokes V leakage of 0.056%. Our linear polarisation (Stokes Q and Stokes U) image cubes consist of 480 x 97.6 kHz wide planes and have a median rms sensitivity per plane of 10.8mJy/beam at 4' and 2.2mJy/beam at 20"; we estimate the Stokes I to Stokes Q/U leakage to be approximately 0.2%. Here we characterise and publicly release our Stokes I, Q, U and V images in addition to the calibrated uv-data., Comment: 23 figures, 1 table and 29 pages. The catalogues, images and uv-data associated with this data release are publicly available via https://lofar-surveys.org/

Online ad platforms offer budget management tools for advertisers that aim to maximize the number of conversions given a budget constraint. As the volume of impressions, conversion rates and prices vary over time, these budget management systems learn a spend plan (to find the optimal distribution of budget over time) and run a pacing algorithm which follows the spend plan. This paper considers two models for impressions and competition that varies with time: a) an episodic model which exhibits stationarity in each episode, but each episode can be arbitrarily different from the next, and b) a model where the distributions of prices and values change slowly over time. We present the first learning theoretic guarantees on both the accuracy of spend plans and the resulting end-to-end budget management system. We present four main results: 1) for the episodic setting we give sample complexity bounds for the spend rate prediction problem: given $n$ samples from each episode, with high probability we have $|\widehat{\rho}_e - \rho_e| \leq \tilde{O}(\frac{1}{n^{1/3}})$ where $\rho_e$ is the optimal spend rate for the episode, $\widehat{\rho}_e$ is the estimate from our algorithm, 2) we extend the algorithm of Balseiro and Gur (2017) to operate on varying, approximate spend rates and show that the resulting combined system of optimal spend rate estimation and online pacing algorithm for episodic settings has regret that vanishes in number of historic samples $n$ and the number of rounds $T$, 3) for non-episodic but slowly-changing distributions we show that the same approach approximates the optimal bidding strategy up to a factor dependent on the rate-of-change of the distributions and 4) we provide experiments showing that our algorithm outperforms both static spend plans and non-pacing across a wide variety of settings.

Algebraic effects offer a versatile framework that covers a wide variety of effects. However, the family of operations that delimit scopes are not algebraic and are usually modelled as handlers, thus preventing them from being used freely in conjunction with algebraic operations. Although proposals for scoped operations exist, they are either ad-hoc and unprincipled, or too inconvenient for practical programming. This paper provides the best of both worlds: a theoretically-founded model of scoped effects that is convenient for implementation and reasoning. Our new model is based on an adjunction between a locally finitely presentable category and a category of functorial algebras. Using comparison functors between adjunctions, we show that our new model, an existing indexed model, and a third approach that simulates scoped operations in terms of algebraic ones have equal expressivity for handling scoped operations. We consider our new model to be the sweet spot between ease of implementation and structuredness. Additionally, our approach automatically induces fusion laws of handlers of scoped effects, which are useful for reasoning and optimisation., Comment: Extended version of the paper Structured Handling of Scoped Effects in ESOP 2022

The development of programming languages can be quite complicated and costly. Hence, much effort has been devoted to the modular definition of language features that can be reused in various combinations to define new languages and experiment with their semantics. A notable outcome of these efforts is the algebra-based "datatypes a la carte" (DTC) approach. When combined with algebraic effects, DTC can model a wide range of common language features. Unfortunately, the current state of the art does not cover modular definitions of advanced control-flow mechanisms that defer execution to an appropriate point, such as call-by-name and call-by-need evaluation, as well as (multi-)staging. This paper defines latent effects, a generic class of such control-flow mechanisms. We demonstrate how function abstractions, lazy computations and a MetaML-like staging can all be expressed in a modular fashion using latent effects, and how they can be combined in various ways to obtain complex semantics. We provide a full Haskell implementation of our effects and handlers with a range of examples., Comment: extended version of APLAS 2021 paper

Delimited control is a powerful mechanism for programming language extension which has been recently proposed for Prolog (and implemented in SWI-Prolog). By manipulating the control flow of a program from inside the language, it enables the implementation of powerful features, such as tabling, without modifying the internals of the Prolog engine. However, its current formulation is inadequate: it does not capture Prolog's unique non-deterministic nature which allows multiple ways to satisfy a goal. This paper fully embraces Prolog's non-determinism with a novel interface for disjunctive delimited control, which gives the programmer not only control over the sequential (conjunctive) control flow, but also over the non-deterministic control flow. We provide a meta-interpreter that conservatively extends Prolog with delimited control and show that it enables a range of typical Prolog features and extensions, now at the library level: findall, cut, branch-and-bound optimisation, probabilistic programming,..., Comment: Pre-proceedings paper presented at the 31st International Symposium on Logic-Based Program Synthesis and Transformation (LOPSTR 2021), Tallinn, Estonia, and Virtual, September 7-8, 2021 (arXiv:2107.10160). arXiv admin note: substantial text overlap with arXiv:2009.04909