A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Graph-based approach repairs programs from diagnostic feedback.
Graph neural network predicts JavaScript types with high accuracy.
This paper presents a novel end-to-end approach to program repair based on sequence-to-sequence learning. We devise, implement, and evaluate a system, called SequenceR, for fixing bugs based on sequence-to-sequence learning on source code. This approach uses the copy mechanism to overcome the unlimited vocabulary probl…
Motivated by the problem of automated repair of software vulnerabilities, we propose an adversarial learning approach that maps from one discrete source domain to another target domain without requiring paired labeled examples or source and target domains to be bijections. We demonstrate that the proposed adversarial l…
MACER accelerates error repair by modularly identifying and applying fixes.
Develops deep learning for logical code segmentation.
In this study we model the warranty claims process and evaluate the warranty servicing costs under non-renewing and renewing free repair warranties. We assume that the repair time for rectifying the claims is non-zero and the repair cost is a function of the length of the repair time. To accommodate the ageing of the p…
Due to its potential to improve programmer productivity and software quality, automated program repair has been an active topic of research. Newer techniques harness neural networks to learn directly from examples of buggy programs and their fixes. In this work, we consider a recently identified class of bugs called va…
New method to recover over-parameterized models corrupted during estimation.
RVAE detects and repairs corrupted cells in mixed-type tabular data.
Proposes a method to repair arbitrage in option prices data.
CLSVAE repairs systematic errors in images with minimal labeled data.
REPAIR mitigates variance collapse to enable linear interpolation between SGD solutions.
SED integrates synthesis, execution, and debugging for neural program synthesis.
Graph2Diff neural network predicts precise code changes for build errors.
SnareNet adds repair layers to neural networks to ensure outputs meet physical constraints.
LLMs excel at summarizing and repairing complex models without needing full models.
CROP verifies clean prefixes in reasoning traces, improving downstream repair accuracy.
CASP improves portfolio optimization by considering asset covariance.
We present a new application and covering number bound for the framework of "Machine Learning with Operational Costs (MLOC)," which is an exploratory form of decision theory. The MLOC framework incorporates knowledge about how a predictive model will be used for a subsequent task, thus combining machine learning with t…
New seq2seq model can copy entire spans, outperforming simpler models in editing tasks.
Neural network identifies undeclared variables and infers their types.
Generative model learns diverse fixes for program errors.
Deep reinforcement learning has led to several recent breakthroughs, though the learned policies are often based on black-box neural networks. This makes them difficult to interpret and to impose desired specification constraints during learning. We present an iterative framework, MORL, for improving the learned polici…
The above named paper has been withdrawn. A colleague has observed a gap in the proof of isotopy invariance, which can be repaired by reducing the coefficients (which lie in (1/6)Z) of the antisymmetric kanji with chords incident with more than one component modulo 8Z. An analogous issue arises in considering the effec…
Many modern data-intensive computational problems either require, or benefit from distance or similarity data that adhere to a metric. The algorithms run faster or have better performance guarantees. Unfortunately, in real applications, the data are messy and values are noisy. The distances between the data points are …
Withdrawn May 2005. There is an error in the even-dimensional case of the proof in the April 2005 version. The hoped-for 4-dimensional applications are unlikely to survive the repairs.
Suppose is a compact Riemannian manifold and an arbitrary point. We employ estimates on the volume growth around to prove that the only conformal compactification of is itself.
We study graphs of (generalized) joins and intersections of finitely generated subgroups of a free group. We show how to disprove a lemma of Imrich and Müller on these graphs and how to repair this lemma.
When the performance of a machine learning model varies over groups defined by sensitive attributes (e.g., gender or ethnicity), the performance disparity can be expressed in terms of the probability distributions of the input and output variables over each group. In this paper, we exploit this fact to reduce the dispa…
A complete error analysis of variational integrators is obtained, by blowing up the discrete variational principles, all of which have a singularity at zero time-step. Divisions by the time step lead to an order that is one less than observed in simulations, a deficit that is repaired with the help of a new past-future…
Algorithms learned from data are increasingly used for deciding many aspects in our life: from movies we see, to prices we pay, or medicine we get. Yet there is growing evidence that decision making by inappropriately trained algorithms may unintentionally discriminate people. For example, in automated matching of cand…
This paper addresses the problem of predicting duration of unplanned power outages, using historical outage records to train a series of neural network predictors. The initial duration prediction is made based on environmental factors, and it is updated based on incoming field reports using natural language processing …
Optimal pre-processing reduces disparate impact by minimizing total variation distance.
The Cayley hyperbolic space minimizes volume entropy among finite-volume metrics.
Deep learning detects building defects from images.
The theory of quantum computation can be constructed from the abstract study of anyonic systems. In mathematical terms, these are unitary topological modular functors. They underlie the Jones polynomial and arise in Witten-Chern-Simons theory. The braiding and fusion of anyonic excitations in quantum Hall electron liqu…
New methods for equity fund selection and portfolio construction using mutual fund top holdings.
The complement of an arrangement A of a finite number of affine hyperplanes in complex n-space has the structure of a poset of spaces indexed by the intersection poset, L(A). The space corresponding to G in L(A) is homotopy equivalent to the complement of the hyperplanes in the central arrangement A_G normal to G. This…
This paper corrects errors in UMAP's derivation and explains its properties.
Paper proposes fair ML predictors to avoid discrimination.
Ontology learning is a critical task in industry, dealing with identifying and extracting concepts captured in text data such that these concepts can be used in different tasks, e.g. information retrieval. Ontology learning is non-trivial due to several reasons with limited amount of prior research work that automatica…
Pearson distance fails to be a metric, but can be fixed.
New representations solve a gap in projective structure proof.
New AI method improves anomaly detection across different IIoT sensors.
MODEF combines denoising and verification to defend against adversarial attacks.
PrIU optimizes machine learning model updates after data cleaning.
Neuron Shapley identifies key neurons in deep networks, improving model accuracy and fairness.