Safe neural networks for input-output specifications.
problem Ensuring machine learning models adhere to input-output constraints.
method Designing constrained predictors and combining them safely.
result Demonstrated on synthetic and real-world datasets.
In recent years several trading platforms appeared which provide a backtest engine to calculate historic performance of self designed trading strategies on underlying candle data. The construction of a correct working backtest engine is, however, a subtle task as shown by Maier-Paape and Platen (cf. arXiv:1412.5558 [q-…
This paper extends the earlier work on an oscillating error correction technique. Specifically, it extends the design to include further corrections, by adding new layers to the classifier through a branching method. This technique is still consistent with earlier work and also neural networks in general. With this ext…
Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence generation paradigm similar to neural machine translation, in which sequence-to-sequence models are …
LLMs struggle with zero-shot annotation tasks due to model-internalized priors.
problem Impact of model-internalized priors on LLM performance in zero-shot annotation tasks.
method Investigated three dimensions: familiarity, decision stickiness, and susceptibility to misaligned task definitions.
result Nearly two-thirds of zero-shot errors are resistant to correction, with a rescue rate of 34.8%. Definition-Specific Familiarity (DSF) shows a positive association with model performance.
Corrects bias in LLM-as-a-judge evaluations using adaptive calibration.
problem Bias in LLM evaluations due to imperfect sensitivity and specificity.
method Plug-in framework with confidence intervals accounting for test and calibration dataset uncertainties.
result LML-based evaluation yields more reliable estimates than human-only evaluation.
Single model corrects JPEG artifacts for various compression settings.
problem JPEG compression artifacts due to aggressive quantization.
method Parameterized architecture using quantization matrix.
result State-of-the-art performance across different quality settings.
Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. Its importance has further increased recently due to the growing need for large-scale datasets to train deep learning models. Weak or noisy supervision could originate from multiple sources i…
Deep reinforcement learning has made significant progress in the field of continuous control, such as physical control and autonomous driving. However, it is challenging for a reinforcement model to learn a policy for each task sequentially due to catastrophic forgetting. Specifically, the model would forget knowledge …
CRC improves multivariate forecasting accuracy without risking performance degradation.
problem Systematic errors and lack of guarantees in multivariate forecasters.
method CRC uses a causality-inspired encoder and hybrid corrector with a safety mechanism.
result CRC consistently improves accuracy and ensures high non-degradation rates.
Recently deep neural networks have been successfully used for various classification tasks, especially for problems with massive perfectly labeled training data. However, it is often costly to have large-scale credible labels in real-world applications. One solution is to make supervised learning robust with imperfectl…
LLMs translate natural language trading intents into correct option strategies using a domain-specific language.
problem Challenges in translating natural language trading intents into correct option strategies due to the complexity of option chain data.
method Introduce Option Query Language (OQL) as a domain-specific intermediate representation to abstract option markets into high-level primitives under grammatical rules. Use LLMs as semantic parsers and validate queries by an engine.
result Significantly improves execution accuracy and logical consistency over direct baselines.
This work explores test-time scaling strategies for LLMs, improving sample efficiency and expressiveness.
problem Understanding the sample efficiency and expressiveness of test-time scaling strategies for LLMs.
method Established separation and expressiveness results for self-consistency, best-of-n, and self-correction strategies. result Self-correction enables Transformers to simulate online learning over multiple tasks without prior knowledge.
Study proposes a new method to estimate bias-correction term for ATE estimation.
problem Estimating the bias-correction term for ATE estimation.
method Directly estimating the bias-correction term by minimizing Bregman divergence.
result Automatic covariate balancing property achieved through specific model choices.
Deep learning improves low-fidelity dynamical models with scarce high-fidelity data.
problem Improving low-fidelity models with limited high-fidelity data.
method Transfer learning using a deep neural network to correct a low-fidelity model.
result An improved DNN model with high accuracy to underlying dynamics.
DisCor corrects reinforcement learning issues by re-weighting collected data.
problem Reinforcement learning algorithms struggle with instability and sensitivity to hyperparameters.
method DisCor reweights collected data to mitigate issues caused by the distribution of experience.
result DisCor improves reinforcement learning in challenging settings like multi-task learning and noisy reward signals.
Sig-PCA integrates model outputs and observations to correct model biases.
problem Improving model accuracy and reliability by correcting biases and numerical approximations.
method Sig-PCA framework that combines summary statistics from model outputs with localized observations via a neural network.
result Corrects model outputs to align closely with observational data, preserving essential statistical information.
Learning robot objective functions from human input has become increasingly important, but state-of-the-art techniques assume that the human's desired objective lies within the robot's hypothesis space. When this is not true, even methods that keep track of uncertainty over the objective fail because they reason about …
Machine learning identifies string models with correct gauge groups and chiral asymmetry.
problem Identifying string models with correct gauge groups and chiral asymmetry.
method Supervised and unsupervised learning of neural networks and auto-encoders.
result Small neural networks can distinguish correct models from random ones.
Corrected samplers reduce discretization error in discrete flow models without additional computational cost.
problem Discretization error in samplers for discrete flow models.
method Established non-asymptotic error bounds for samplers, proposed time-corrected and location-corrected samplers.
result Location-corrected sampler has lower complexity and better generation quality.
Reasoning models generate differently based on problem difficulty, not just length.
problem Understanding how reasoning models handle different problem difficulties.
method Examined hidden-state trajectories across competitive programming, mathematics, and Boolean satisfiability.
result Corrected trajectory geometry shows difficulty-dependent differences in reasoning models, with stronger effects in the code domain.
The paper proves an obstruction to immersed curves with specific curvature.
problem Existence of immersed curves with prescribed curvature.
method Proofs and corrections of submitted manuscript.
result An obstruction to the existence of immersed curves of prescribed curvature.
Corrects errors in ILA for Bayesian inference in LGMs.
problem Error in ILA for non-Gaussian likelihoods in LGMs.
method Importance sampling scheme to correct ILA errors.
result Corrected posterior converges to the true posterior with increased samples.
Paper tackles graph matching with partially correct seeds, improving performance guarantees.
problem Graph matching with partially correct seeds.
method Proposes algorithms for matching vertices based on 1-hop and 2-hop neighborhoods, analyzing their performance guarantees.
result New 2-hop algorithm requires fewer correct seeds than the 1-hop algorithm, especially for sparse graphs.
Construct quaternionic-Kähler metrics from special Kähler manifolds with specific BPS structure variations.
problem Construct quaternionic-Kähler metrics from special Kähler manifolds with mutually local variations of BPS structures.
method Construct quaternionic-Kähler metrics from a conical special Kähler manifold with a certain type of mutually-local variation of BPS structures. Provide global and local explicit formulas for the quaternionic-Kähler metric.
result Construct quaternionic-Kähler metrics that are positive-definite and deform the 1-loop corrected Ferrara-Sabharval metric.
Proposes PRMs for interpreting financial risk concept drift.
problem Concept drift in high-stakes predictions like credit risk.
method Probabilistic Rule Models (PRMs) using Markov Logic Networks.
result Interpretable rules explain borrower risk changes.
Machine learning models predict brain age with systematic bias, corrected in this study.
problem Systematic bias in machine learning regression models for brain age prediction.
method General constrained optimization approach to correct bias.
result Our method effectively eliminates the bias from brain age predictions.
Improved local multivariable regression for better inference with limited data.
problem Limited sample size hampers local polynomial/multivariable regression.
method Prediction-Powered Inference (PPI) algorithm for local multivariable regression.
result Significantly reduces estimation variance without increasing error.
In this work, we addressed the issue of applying a stochastic classifier and a local, fuzzy confusion matrix under the framework of multi-label classification. We proposed a novel solution to the problem of correcting label pairwise ensembles. The main step of the correction procedure is to compute classifier- specific…
Interest prohibition theory concerns theoretical aspects of interest prohibition. We attempt to lay down some aspects of interest prohibition theory wrapped in a larger framework of informal logic. The reason for this is that interest prohibition theory has to deal with a variety of arguments which is so wide that a li…
GrowNet uses shallow neural networks for gradient boosting, outperforming existing methods.
problem Improving gradient boosting performance through shallow neural networks.
method Unified gradient boosting framework with shallow neural networks as weak learners, incorporating corrective steps.
result GrowNet outperformed state-of-the-art boosting methods in classification, regression, and learning to rank tasks.
Improved variational inference for geophysical inverse problems with data correction.
problem High computational cost and accuracy issues in Bayesian inference for geophysical inverse problems.
method Amortized variational inference with latent distribution correction using physics-based priors.
result Improved robustness of amortized variational inference under data distribution shifts.
The study identifies latent concepts from diverse observations without assuming specific models.
problem Lack of general theoretical support for concept learning.
method Develops a nonparametric framework for identifying latent concepts from multiple classes of observations.
result Correctness guarantees for concept identification without parametric assumptions.
Certified guidance ensures generative models always meet planning objectives.
problem Lack of guarantees for generated outputs satisfying planning objectives.
method Certified guidance modifies generative models without retraining, ensuring outputs meet STL specifications.
result Certified guidance produces models that are always correct, unlike non-certified methods.
New method improves robustness of double robust estimators under complete misspecification.
problem Improper performance of double robust estimators when all nuisance functions are misspecified.
method DR+ACC, an adaptive correction clipping method.
result DR+ACC ensures bounded error and maintains semiparametric efficiency.
Kernel balancing weights are generalized as KRRR, providing better confidence intervals for treatment effects.
problem Lack of generalization error, correct feature specification, and limited to average effects.
method Interpreting kernel balancing weights as KRRR, relaxing feature specification, and extending Gaussian approximation.
result KRRR provides strong generalization properties and justifies confidence sets for causal functions.
In 1980 J. Powell proposed that five specific elements sufficed to generate the Goeritz group of any Heegaard splitting of S3, extending work of Goeritz on genus 2 splittings. Here we prove that Powell's conjecture was correct for splittings of genus 3 as well, and discuss a framework for deciding the truth of t…
We present a novel framework for specifying and verifying correctness globally for neural networks on perception tasks. Most previous works on neural network verification for perception tasks focus on robustness verification. Unlike robustness verification, which aims to verify that the prediction of a network is stabl…
Study corrects previous work on knot Floer homology of certain pretzel knots.
problem Computing the Knot Floer Homology of specific pretzel knots.
method Applied peculiar modules theory for Floer homology of 4-ended tangles, using immersed curve interpretation.
result Corrected the rank of Knot Floer Homology for some pretzel knots.
Suppose that multiple experts (or learning algorithms) provide us with alternative Bayesian network (BN) structures over a domain, and that we are interested in combining them into a single consensus BN structure. Specifically, we are interested in that the consensus BN structure only represents independences all the g…
CUTS removes corruption from models without clean data, improving utility and security.
problem Removing corruption from models without access to clean training data.
method CUTS uses a proxy set to amplify corruption and subtract it from model weights.
result CUTS recovers a large fraction of lost utility and nearly eliminates attacks with minimal damage.
Efficient policy learning from observational data using weighted classification reductions.
problem Efficient policy evaluation does not necessarily lead to efficient estimation of policy parameters.
method Proposed an estimation approach based on generalized method of moments, efficient for policy parameters.
result Demonstrated empirical efficiency and regret benefits of a proposed method.
Motivated by community detection, we characterise the spectrum of the non-backtracking matrix B in the Degree-Corrected Stochastic Block Model. Specifically, we consider a random graph on n vertices partitioned into two equal-sized clusters. The vertices have i.i.d. weights {φu}u=1n with second moment $Φ…
After being trained, classifiers must often operate on data that has been corrupted by noise. In this paper, we consider the impact of such noise on the features of binary classifiers. Inspired by tools for classifier robustness, we introduce the same classification probability (SCP) to measure the resulting distortion…
New method for community detection in graphs faster than DCBM inference.
problem Efficiently detecting communities in graphs with heterogeneous node degrees.
method Reformulated constrained nonnegative matrix factorization for DCBM inference.
result Faster community detection (4 minutes for 100k nodes vs. DCBM's 10+ minutes).
New methods reduce bias in machine learning predictions for causal inference without extra data.
problem Machine learning predictions from satellite data shrink toward the mean, leading to biased causal estimates.
method Two post-hoc correction methods: Linear Calibration Correction (LCC) and Tweedie's approach, reduce shrinkage-induced bias.
result Tweedie's method yields nearly unbiased treatment-effect estimates, enabling multiple trials with a single map.
We consider the problem of learning fair decision systems in complex scenarios in which a sensitive attribute might affect the decision along both fair and unfair pathways. We introduce a causal approach to disregard effects along unfair pathways that simplifies and generalizes previous literature. Our method corrects …
A new transformer model corrects diacritics and typos in multiple languages.
problem Restoring diacritics and correcting typos in online communications.
method Employing a universal ByT5 transformer model trained on 12 languages, including Lithuanian.
result Achieves > 98% accuracy in diacritics restoration and typos correction.