Declarative entropy constraints improve semi-supervised learning.
problem Improving semi-supervised learning performance.
method Declarative specification of entropy constraints for semi-supervised learning.
result Consistent improvements on SSL benchmarks, including a new state-of-the-art result.
DisCoveR efficiently discovers declarative process models from event logs.
problem Mining declarative process models from event logs efficiently and accurately.
method DisCoveR precisely formalizes an algorithm, uses a bit vector implementation, and rigorously evaluates performance.
result DisCoveR outperforms other declarative miners in accuracy and runtime.
The paper introduces a new language for semi-supervised learning tasks.
problem Handling semi-supervised learning with declarative constraints.
method Developed a declarative language for modeling both supervised and semi-supervised learning tasks, including heuristics and combining multiple heuristics.
result Improved performance on relation-extraction tasks for real-world domains.
The study compares ASP encodings for sequential pattern mining tasks.
problem Efficiency of Answer Set Programming (ASP) encodings for sequential pattern mining.
method Two representations of embeddings (fill-gaps vs skip-gaps) and various types of patterns were tested.
result Fill-gaps strategy is more efficient on real problems due to lower memory consumption.
DyNet allows dynamic construction of neural networks in C++ or Python.
problem Implementing complex neural network architectures in static declaration toolkits.
method Dynamic declaration of network structures, optimized C++ backend, lightweight graph representation.
result DyNet achieves faster speeds than static declaration toolkits and Chainer.
The paper explores how to learn models that respect constraints in probabilistic learning.
problem Learning models that respect declared constraints in probabilistic learning.
method Mathematical inquiry on tractable probabilistic models like sum-product networks.
result Determines conditions under which constraints can be integrated with model learning.
Ludwig simplifies deep learning for non-experts.
problem Making deep learning accessible to non-experts.
method Type-based data abstraction and declarative configuration files.
result Ludwig democratizes deep learning, making it accessible to a broader audience.
This dissertation uses ILP to learn Bayesian network structures efficiently.
problem Learning the structure of Bayesian networks from data.
method Integer Linear Programming formulation with cluster constraints and cutting planes.
result The approach finds feasible solutions for Bayesian network structures efficiently.
We study the pricing problem for corporate defaultable bond from the viewpoint of the investors outside the firm that could not exactly know about the information of the firm. We consider the problem for pricing of corporate defaultable bond in the case when the firm value is only declared in some fixed discrete time a…
A framework for analyzing financial systems under scenario constraints.
problem Quantifying worst-case and best-case performance in financial systems.
method Quantitative automata-based framework integrating event history automata and weighted finance finite automata.
result Exact calculation of upper and lower payoff bounds with interpretable witness event histories.
Asymmetry PRISM outperforms CPU and GPU solvers for institutional rebalancing.
problem Institutional rebalancing with deadline constraints
method Asymmetry PRISM
result Asymmetry PRISM-CPU is 4.5x to 24.1x faster than the fastest completed reference row in the same lane.
Probabilistic programming allows specification of probabilistic models in a declarative manner. Recently, several new software systems and languages for probabilistic programming have been developed on the basis of newly developed and improved methods for approximate inference in probabilistic models. In this contribut…
Blang simplifies Bayesian analysis for non-standard data types.
problem Bayesian inference for non-standard data structures.
method Bayesian declarative language, distribution continua, sequential Monte Carlo, non-reversible MCMC.
result Bayesian analysis on arbitrary data types is feasible and efficient.
Algorithm learns data structure in real-time with outliers and change points.
problem Sequential online prediction in the presence of outliers and change points.
method INTEL algorithm using WGPs and POE model for real-time structure learning.
result Significantly better performance than benchmarks in real datasets.
Paper augments neural nets with logic for improved performance.
problem Training neural networks with declarative knowledge without extra parameters.
method Systematically compiles logical statements into computation graphs that augment neural networks.
result Knowledge-augmented networks significantly improve performance, especially in low-data scenarios.
The paper evaluates income credibility using a hierarchical correlation reconstruction technique.
problem Automatic evaluation of credibility of exogenous variables like income based on endogenous variables.
method Adapted hierarchical correlation reconstruction technique for credibility evaluation, combining statistics with machine learning.
result The method allows for the automatic evaluation of credibility of income data, with high density values considered credible.
Tensor models decode human perception and memory using SPO triples.
problem Understanding implicit and explicit perception and memory in the brain.
method Tensor models with SPO triples, dual representations, and four layers.
result Semantic memory is crucial for explicit perception and declarative memories.
New architecture separates object state and behavior for better game dynamics.
problem Lack of systematicity in black-box models for dynamic environments.
method Factorizes declarative and procedural knowledge into object files and schemata.
result Improves generalization on environments with multiple object tokens.
TensorFlow Probability introduces JointDistributions for probabilistic programming.
problem Specifying models in probabilistic programming languages.
method Declarative representations of directed graphical models.
result JointDistributions for TensorFlow Probability.
Adapts safe policies for exploration in high-risk settings.
problem Balancing safety and exploration in high-risk environments.
method Uses conformal calibration on a safe reference policy to determine aggressive action limits.
result Safe exploration improves performance without requiring model class identification or hyperparameter tuning.
LIC compiles probabilistic models to generate efficient MCMC proposals.
problem Creating accurate Metropolis-Hastings proposals for Bayesian inference.
method Integrates probabilistic graphical models and neural networks in an open-source framework to optimize proposal distributions.
result LIC produces more efficient and robust MCMC proposals compared to existing methods.
Paper uses social norms to teach robots human behavior.
problem Teaching robots to behave like humans in society.
method Captured social norms guide reinforcement learning towards normative behavior.
result Robots can learn normative behavior through automatic norm reward system.
Two kernel Stein tests control decision errors in non-parametric model comparison.
problem Non-parametric multiple model comparison.
method Two statistical tests controlling false positive and false discovery rates.
result The first test has a higher true positive rate than the second under appropriate conditions.
Comment on a theorem about surface determination from map data.
problem Determining a Riemann surface from its Dirichlet-to-Neumann map.
method Critical remarks on a specific theorem.
result Criticism of a key theorem's validity.
Helix speeds up iterative ML development by optimizing workflow execution.
problem Inefficient manual tuning of ML workflows.
method Declarative system that optimizes workflow execution end-to-end and across iterations, minimizing runtime per iteration.
result Up to an order of magnitude reduction in cumulative run time compared to state-of-the-art tools.
We formalize causal separation in portfolio theory, deriving a closed-form projected Markowitz solution.
problem Portfolio optimization under causal separation conditions.
method Derive a closed-form solution for portfolio optimization using causal separation conditions.
result A closed-form projected Markowitz solution is derived under causal separation conditions.
GENO framework generates efficient solvers for machine learning problems.
problem Designing efficient solvers for machine learning problems.
method GENO framework combines a modeling language with a generic solver to generate solvers from optimization problem specifications.
result Automatically generated solvers are as efficient as well-engineered specialized solvers and orders of magnitude more efficient than classical modeling language plus solver approaches.
Agents learn to execute programs grounded in their environment.
problem Executing programs with unknown objects.
method Deep RL agents that ground program terms in environment.
result Agents generalize to new, unseen objects.
We consider an insurance entity endowed with an initial capital and a surplus process modelled as a Brownian motion with drift. It is assumed that the company seeks to maximise the cumulated value of expected discounted dividends, which are declared or paid in a foreign currency. The currency fluctuation is modelled as…
A new method for math reasoning that allows for iterative correction.
problem Standard reasoning models commit to each token and cannot recover from early errors.
method Generative framework with latent thought vectors for iterative self-correction.
result 30 rethinking iterations surpass baselines with 15 times more parameters.
Forecastability measures predictive information across horizons.
problem How much predictive information is available at each prediction horizon?
method Develops the consequences of mutual information between future observations and information set.
result Forecastability is a profile reflecting process dependence structure, with properties like compression and truncation error.
The Euclidean cone metrics coming from q-differentials on a closed surface of genus g > 1 define an equivalence relation on homotopy classes of closed curves declaring two to be equivalent if they have the equal length in every such metric. We prove an analog of the result of Randol for hyperbolic metrics (building on …
Improved portfolio optimization reduces sensitivity to neural network initialization.
problem High sensitivity to neural network initialization in portfolio optimization.
method Robust end-to-end framework for risk budgeting portfolios.
result Enhanced stability in portfolio optimization without compromising performance.
Paper uses clustering to predict student attrition in CSUN departments.
problem Identifying at-risk students to increase graduation rates.
method Unsupervised clustering of lower division courses.
result Detected hidden bottleneck courses for each major.
Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs and RNNs) with declarative first-order logic rules. Specifically, we develop…
The paper investigates herding behavior in cryptocurrency markets.
problem Cryptocurrency prices are influenced by herding behavior.
method The study uses the Markov-Switching approach to test herding behavior under asymmetric and symmetric conditions.
result Cryptocurrency prices are driven by herding behavior.
CUBE explains models by balanced experiments and contrasts.
problem Post-hoc explanation of trained predictive models.
method Design-based framework using balanced low-high probes.
result Reveals dominant learned effect structure and clarifies query efficiency.
Study tests five popular trading signal families and finds four refuted, one inconclusive, and one not refuted.
problem Testing the viability of five popular trading signal families for generating a positive edge.
method Statistical edge testing, economic viability assessment, and finite-bankroll survival under leverage using exposure-matched benchmarks, stationary-bootstrap confidence intervals, and hierarchical Benjamini-Yekutieli control.
result Four out of five signal families are refuted, one is inconclusive, and one is not refuted.
Study on Parisian ruin with hybrid observation times.
problem Calculating Parisian ruin under a hybrid observation scheme.
method Hybrid observation scheme with Poisson arrivals and continuous monitoring below zero.
result Improved results and fluctuation identities in terms of second-generation scale functions.
We propose a novel non-parametric adaptive anomaly detection algorithm for high dimensional data based on rank-SVM. Data points are first ranked based on scores derived from nearest neighbor graphs on n-point nominal data. We then train a rank-SVM using this ranked data. A test-point is declared as an anomaly at alpha-…
We explore completely exceptional 2nd order scalar PDEs and their connection to Monge-Ampère equations.
problem Identifying a specific class of nonlinear PDEs that are not genuinely nonlinear.
method Unified geometric background review and definition of completely exceptional PDEs and Monge-Ampère equations.
result The class of completely exceptional 2nd order scalar PDEs reduces to Monge-Ampère equations.
Study explores how labour income impacts optimal bankruptcy strategy.
problem Optimal bankruptcy strategy for agents with varying labour income.
method Solved analytically using the duality method, analyzed sensitivity to cost and benefit parameters.
result Introducing labour income affects optimal strategies, revealing new insights.
Paper proposes a visual tool for analyzing financial markets.
problem Rational negligence in financial markets during the 2008 crisis.
method Visual declarative language based on port-graph rewriting.
result Visual tool for analyzing asset-backed securities.
The large majority of risk-sharing transactions involve few agents, each of whom can heavily influence the structure and the prices of securities. This paper proposes a game where agents' strategic sets consist of all possible sharing securities and pricing kernels that are consistent with Arrow-Debreu sharing rules. F…
We propose a non-parametric anomaly detection algorithm for high dimensional data. We score each datapoint by its average K-NN distance, and rank them accordingly. We then train limited complexity models to imitate these scores based on the max-margin learning-to-rank framework. A test-point is declared as an anomaly…
The restricted isometry property (RIP) for design matrices gives guarantees for optimal recovery in sparse linear models. It is of high interest in compressed sensing and statistical learning. This property is particularly important for computationally efficient recovery methods. As a consequence, even though it is in …
We propose a non-parametric anomaly detection algorithm for high dimensional data. We first rank scores derived from nearest neighbor graphs on n-point nominal training data. We then train limited complexity models to imitate these scores based on the max-margin learning-to-rank framework. A test-point is declared as…
The tangent bundle TkM of order k, of a smooth Banach manifold M consists of all equivalent classes of curves that agree up to their accelerations of order k. For a Banach manifold M and a natural number k first we determine a smooth manifold structure on TkM which also offers a fiber bundle structure f…