Search Results for author:
Found 22 papers, 4 papers with code
Safe Learning of PDDL Domains with Conditional Effects -- Extended Version
We prove that learning non-trivial safe action models with conditional effects may require an exponential number of samples.
Distribution-Specific Auditing For Subgroup Fairness
In this work, we give positive and negative results on auditing for Gaussian distributions: On the positive side, we present an alternative approach to leverage these advances in agnostic learning and thereby obtain the first polynomial-time approximation scheme (PTAS) for auditing nontrivial combinatorial subgroup fairness: we show how to audit statistical notions of fairness over homogeneous halfspace subgroups when the features are Gaussian.
Learnability with PAC Semantics for Multi-agent Beliefs
To circumvent the negative results in the literature on the difficulty of robust learning with the PAC semantics, we consider so-called implicit learning where we are able to incorporate observations to the background theory in service of deciding the entailment of an epistemic query.
Hardness of Maximum Likelihood Learning of DPPs
In seminal work on DPPs in Machine Learning, Kulesza conjectured in his PhD Thesis (2011) that the problem of finding a maximum likelihood DPP model for a given data set is NP-complete.
An Example of the SAM+ Algorithm for Learning Action Models for Stochastic Worlds
In this technical report, we provide a complete example of running the SAM+ algorithm, an algorithm for learning stochastic planning action models, on a simplified PPDDL version of the Coffee problem.
Conditional Linear Regression for Heterogeneous Covariances
Often machine learning and statistical models will attempt to describe the majority of the data.
Provable hierarchical lifelong learning with a sketch-based modular architecture
We propose a modular architecture for lifelong learning of hierarchically structured tasks.
Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions
Many reinforcement learning (RL) environments in practice feature enormous state spaces that may be described compactly by a "factored" structure, that may be modeled by Factored Markov Decision Processes (FMDPs).
Safe Learning of Lifted Action Models
However, model learning approaches frequently do not provide safety guarantees: the learned model may assume actions are applicable when they are not, and may incorrectly capture actions' effects.
One Network Fits All? Modular versus Monolithic Task Formulations in Neural Networks
Can deep learning solve multiple tasks simultaneously, even when they are unrelated and very different?
Probabilistic Generating Circuits
Generating functions, which are widely used in combinatorics and probability theory, encode function values into the coefficients of a polynomial.
Learning Implicitly with Noisy Data in Linear Arithmetic
In this work, we extend implicit learning in PAC-Semantics to handle noisy data in the form of intervals and threshold uncertainty in the language of linear arithmetic.
List Learning with Attribute Noise
We introduce and study the model of list learning with attribute noise.
Query-driven PAC-Learning for Reasoning
We consider the problem of learning rules from a data set that support a proof of a given query, under Valiant's PAC-Semantics.
Implicitly Learning to Reason in First-Order Logic
We consider the problem of answering queries about formulas of first-order logic based on background knowledge partially represented explicitly as other formulas, and partially represented as examples independently drawn from a fixed probability distribution.
Polynomial-time probabilistic reasoning with partial observations via implicit learning in probability logics
In this work we consider the use of bounded-degree fragments of the "sum-of-squares" logic as a probability logic.
Conditional Sparse $\ell_p$-norm Regression With Optimal Probability
We consider the following conditional linear regression problem: the task is to identify both (i) a $k$-DNF condition $c$ and (ii) a linear rule $f$ such that the probability of $c$ is (approximately) at least some given bound $\mu$, and $f$ minimizes the $\ell_p$ loss of predicting the target $z$ in the distribution of examples conditioned on $c$.
Conditional Linear Regression
Work in machine learning and statistics commonly focuses on building models that capture the vast majority of data, possibly ignoring a segment of the population as outliers.
Learning Abduction under Partial Observability
The main shortcoming of this formulation of the task is that it assumes access to full-information (i. e., fully specified) examples; relatedly, it offers no role for declarative background knowledge, as such knowledge is rendered redundant in the abduction task by complete information.
Efficient, Safe, and Probably Approximately Complete Learning of Action Models
In this paper we explore the theoretical boundaries of planning in a setting where no model of the agent's actions is given.
Conditional Sparse Linear Regression
Machine learning and statistics typically focus on building models that capture the vast majority of the data, possibly ignoring a small subset of data as "noise" or "outliers."
PAC Quasi-automatizability of Resolution over Restricted Distributions
The learning setting we consider is a partial-information, restricted-distribution setting that generalizes learning parities over the uniform distribution from partial information, another task that is known not to be achievable directly in various models (cf.
