Code-generating large language models map natural language to code. However, only a small portion of the infinite space of naturalistic utterances is effective at guiding code generation. For non-expert end-user programmers, learning this is the challenge of abstraction matching. We examine this challenge in the specific context of data analysis in spreadsheets, in a system that maps the user’s natural language query to Python code using the Codex generator, executes the code, and shows the result. We propose grounded abstraction matching, which bridges the abstraction gap by translating the code back into a systematic and predictable naturalistic utterance. In a between-subjects, think-aloud study (n=24), we compare grounded abstraction matching to an ungrounded alternative based on previously established query framing principles. We find that the grounded approach improves end-users’ understanding of the scope and capabilities of the code-generating model, and the kind of language needed to use it effectively.

Spreadsheet errors are ubiquitous and costly, an unfortunate combination that is well-reported. A large class of these errors can be attributed to the inability to clearly see the underlying computational structure, as well as poor support for abstraction (encapsulation, re-use, etc). In this paper we propose a novel solution: a multiple-representation spreadsheet containing additional representations that allow abstract operations, without altering the conventional grid representation or its formula syntax. Through a user study, we demonstrate that the use of multiple representations can significantly improve user performance when performing spreadsheet authoring and debugging tasks. We close with a discussion of design implications and outline future directions for this line of inquiry.

As programmers, programming in typed languages increases our confidence in the correctness of our programs. As type system designers, soundness proofs increase our confidence in the correctness of our type systems. There is more to typed languages than their typing rules, however. To be usable, a typed language needs to provide a well-furnished standard library and to specify types for its exports.

This paper presents Bayesian edge inference (BEI), a single frame super resolution method explicitly grounded in Bayesian inference that addresses issues common to existing methods. Though the best give excellent results at modest magnification factors, they suffer from gradient stepping and boundary coherence problems by factors of 4x. Central to BEI is a causal framework that allows image capture and recapture to be modeled differently, a principled way of undoing downsampling blur, and a technique for incorporating Markov random field potentials arbitrarily into Bayesian networks. Besides addressing gradient and boundary issues, BEI is shown to be competitive with existing methods on published correctness measures. The model and framework are shown to generalize to other reconstruction tasks by demonstrating BEI's effectiveness at CCD demosaicing and inpainting with only trivial changes.

This paper shows that the basic Hough transform is implicitly a Bayesian process-that it computes an unnormalized posterior distribution over the parameters of a single shape given feature points. The proof motivates a purely Bayesian approach to the problem of finding parameterized shapes in digital images. A proof-of-concept implementation that finds multiple shapes of four parameters is presented. Extensions to the basic model that are made more obvious by the presented reformulation are discussed.

Developing quantum algorithms has proven to be very difficult. In this paper, the concept of using classical machine learning techniques to derive quantum operators from examples is presented. A gradient descent algorithm for learning unitary operators from quantum state pairs is developed as a starting point to aid in developing quantum algorithms. The algorithm is used to learn the quantum Fourier transform, an underconstrained two-bit function, and Grover's iterate.

Image interpolation algorithms try to fit a function to a matrix of samples in a "natural-looking" way. This paper presents edge inference, an algorithm that does this by mixing neural network regression with standard image interpolation techniques. Results on gray level images are presented, and it is demonstrated that edge inference is capable of producing sharp, natural-looking results. A technique for reintroducing noise is given, and it is shown that, with noise added using a bicubic interpolant, edge inference can be regarded as a generalization of bicubic interpolation. Extension into RGB color space and additional applications of the algorithm are discussed, and some tips for optimization are given.