This paper shows how procedural level generation improves deep RL models' generalization.
problem Deep RL models overfit to fixed environments, failing to generalize to new levels.
method Procedurally generated levels during training to enhance generalization.
result Procedural level generation enables better generalization to new levels and improved performance with less data.
Reinforcement learning improves game level design.
problem Creating high-quality game levels with limited examples.
method Transforming level design into a Markov decision process and training with reinforcement learning.
result Trained reinforcement learning agents can generate high-quality levels quickly.
TOAD-GAN generates coherent game levels from a single example.
problem Creating game levels from a single example.
method Token-based Procedural Content Generation (PCG) using SinGAN architecture.
result Achieves state-of-the-art results in generating coherent levels of similar style.
Optimal ridge regularization computed iteratively from generative parameters.
problem Finding the optimal ridge regularization strength for linear regression.
method Iterative procedure to compute optimal regularization strength numerically.
result The proposed procedure attains near-optimal generalization across various conditions.
New PCGML approach generates novel game content across multiple platformer domains.
problem Generating novel game content in new domains.
method Using a new affordance and path vocabulary, variational autoencoders trained on data from six platformer games produce new content with varying proportions of different domains.
result Captures latent level space spanning multiple domains and generates new content with varying proportions of different domains.
We propose an extension to Hawkes processes by treating the levels of self-excitation as a stochastic differential equation. Our new point process allows better approximation in application domains where events and intensities accelerate each other with correlated levels of contagion. We generalize a recent algorithm f…
Estimating the level set of a signal from measurements is a task that arises in a variety of fields, including medical imaging, astronomy, and digital elevation mapping. Motivated by scenarios where accurate and complete measurements of the signal may not available, we examine here a simple procedure for estimating the…
Proposes a new method to control FDR using frequentist-assisted horseshoe for high-dimensional testing.
problem Designing tests with frequentist false discovery rate control using horseshoe prior.
method Frequentist-assisted horseshoe procedure for high-dimensional normal means testing.
result Consistently achieves robust finite-sample FDR control in various sparse cases.
A fast method for fitting deep hierarchical models to large datasets.
problem Fitting a deeply-nested hierarchical model to a large book review dataset.
method Moment-based estimator extension for arbitrarily deep hierarchies.
result Orders of magnitude faster than standard maximum likelihood procedures.
The paper develops tests for variable selection using LARS in high dimensions.
problem Variable selection and multiple testing in high-dimensional settings.
method Least Angle Regression (LARS) and post-selection joint law of knots.
result Exact non-asymptotic level testing procedures for variable selection.
Enhances machine learning accuracy with multi-level training data.
problem Improving accuracy of machine learning algorithms for differential equations.
method Combining coarse and fine resolution training data.
result Significant gains in accuracy over single-level algorithms.
We introduce the multiresolution recurrent neural network, which extends the sequence-to-sequence framework to model natural language generation as two parallel discrete stochastic processes: a sequence of high-level coarse tokens, and a sequence of natural language tokens. There are many ways to estimate or learn the …
New method achieves optimal sample complexity without warm-start in bilevel optimization.
problem Optimizing smooth objective functions with fixed point constraints in meta-learning and equilibrium models.
method Fixed point iterations at lower-level and projected inexact gradient descent at upper-level.
result Achieves near optimal sample complexity O(ε−2) and ildeO(ε−1) samples. The paper proposes selective forgetting for deep neural networks at a finer level than samples.
problem Selective forgetting of deep neural networks to handle outliers, poisoned data, or sensitive information.
method Formulated selective forgetting at a finer level than samples, introduced as an optimization problem on three criteria.
result Experimental results show the model can forget specific information for classification, improving accuracy in specific cases.
We consider a statistical model for pairs of traded assets, based on a Cointegrated Vector Auto Regression (CVAR) Model. We extend standard CVAR models to incorporate estimation of model parameters in the presence of price series level shifts which are not accurately modeled in the standard Gaussian error correction mo…
For leveled spatial graphs, we find a surface embedding that allows cellular embedding.
problem Finding a surface embedding for general spatial graphs is not always possible.
method Define leveled property, decompose graph into subgraphs, and construct surface.
result For leveled spatial graphs with a small number of levels, a surface can always be found.
New method uses image-level and pixel-level annotations for brain tumor segmentation.
problem Challenges in obtaining pixel-level annotations for brain tumor segmentation.
method Proposes a learning-based framework that combines both pixel- and image-level annotations.
result Method's performance in segmentation quality is competitive with traditional fully-supervised approach.
The study finds that memorization is necessary or harmful depending on the prior distribution and noise level.
problem The impact of memorization on generalization in overparameterized models.
method An overparameterized linear model with general priors in a Bayesian setup.
result Explicit conditions for optimal generalization based on the prior distribution and noise level.
In many practical applications of multiple hypothesis testing using the False Discovery Rate (FDR), the given hypotheses can be naturally partitioned into groups, and one may not only want to control the number of false discoveries (wrongly rejected null hypotheses), but also the number of falsely discovered groups of …
SIREN protocol corrects optimistic winner's scores in LLM evaluation.
problem Optimistic winner's scores in LLM evaluation due to adaptive benchmarking.
method SIREN protocol that freezes post-search shortlist, separates selection and evaluation, and uses bootstrap for uncertainty quantification.
result SIREN provides valid confidence intervals for procedure-performance curves and deployment conclusions.
The paper tackles online FDR control in hypothesis testing with contextual features.
problem Controlling false discoveries in online hypothesis testing with contextual features.
method Proposes a new class of online testing procedures that learn significance levels sequentially, incorporating contextual information and previous results.
result Proves that the proposed procedures control online FDR under standard assumptions and outperform existing methods in terms of statistical power.
New method uses neural networks to estimate parameters without needing detector simulations.
problem Estimating parameters in high-energy physics with detector effects.
method Two-level fitting approach: SRGN (Simulation-level fit based on Reweighting Generator-level events with Neural networks).
result Demonstrated using simulated datasets, SRGN can estimate parameters without detector effects.
Deep model interprets gene expression from single-cell RNA sequencing.
problem Interpreting gene expression levels from single-cell RNA sequencing data.
method Probabilistic model with neural network conditional distributions, variational inference, stochastic optimization.
result The model outperforms state-of-the-art methods for differential expression analysis.
This paper shows how rotating, cropping, and translating images improves a reinforcement learning agent's ability to generalize.
problem Reinforcement learning agents struggle to generalize to slight variations of their training environments.
method The authors investigate the impact of rotation, translation, and cropping on the input representation of reinforcement learning agents.
result Cropped, translated, and rotated observations lead to better generalization in reinforcement learning agents.
Gonogo offers tools for sensitivity experiments in R.
problem Conducting, analyzing, and simulating sensitivity experiments.
method Suite of R functions for various adaptive procedures.
result Achieving overlapping data and refining testing in distribution tails.
Paper introduces procedural noise for generating adversarial examples that fool deep networks.
problem Vulnerability of deep convolutional networks to adversarial examples.
method Structured approach for generating Universal Adversarial Perturbations (UAPs) with procedural noise.
result Single noise patterns can fool up to 90% of a dataset, with high universal evasion rates.
Introduces six levels of privacy for financial synthetic data.
problem Privacy risks in financial synthetic data.
method Defines six levels of privacy protection for synthetic data.
result Provides a framework to assess and improve privacy in synthetic data.
We apply multiple testing procedures to the validation of estimated default probabilities in credit rating systems. The goal is to identify rating classes for which the probability of default is estimated inaccurately, while still maintaining a predefined level of committing type I errors as measured by the familywise …
FRESH combines patient-level and aggregate-level data for better clinical decision making.
problem Combining patient-level and aggregate-level data for clinical decision making.
method FRESH method that re-calibrates a patient-level model to match specified aggregate statistics.
result Unified data-efficient model for clinical decision making.
A new method for solving complex sequential decision-making problems by decomposing them into multiple levels.
problem Sequential decision-making with natural multi-level structure.
method Multi-level meta-reinforcement learning with skill-based curriculum.
result Efficiently reduces stochasticity and policy search space, leading to fewer iterations and computations.
The paper addresses the gap between theoretical and practical confidence set widths in universal inference.
problem Inference procedures can be overly conservative, leading to wider confidence sets than expected.
method The authors identify the source of asymptotic conservativeness and propose a remedy based on studentization and bias correction.
result The proposed method achieves exact asymptotic coverage at the nominal 1−α level, even under model misspecification. Reference metrics are used to define the differential structure on multicube representations of manifolds, i.e., they provide a simple and practical way to define what it means globally for tensor fields and their derivatives to be continuous. This paper introduces a general procedure for constructing reference metrics…
Paper uses RL for high-level character control in 3D environments.
problem Creating intelligent characters with generalizable behavior.
method Combines traditional animations, heuristics, and reinforcement learning.
result Demonstrates learning of complex behaviors in a 3D environment.
New methods for handling confounding in observational studies.
problem Handling confounding variables in observational studies.
method Generalized coarsened procedures for clustering confounding variables, followed by estimation of treatment effects and variance.
result Developed a general asymptotic framework for the average causal effect estimator and variance formulae.
This study proposes the segmentation procedure of univariate time series based on Fisher's exact test. We show that an adequate change point can be detected as the minimum value of p-value. It is shown that the proposed procedure can detect change points for an artificial time series. We apply the proposed method to fi…
Procedure maps quantum systems to curved spacetimes with resonant frequencies.
problem Mapping quantum mechanics to curved spacetimes with resonant frequencies.
method Klein-Gordonization procedure, reducing to nonlinear elliptic equation.
result Large family of spacetimes with resonant spectra for massless wave equations.
Traditional voxel-level multiple testing procedures in neuroimaging, mostly p-value based, often ignore the spatial correlations among neighboring voxels and thus suffer from substantial loss of power. We extend the local-significance-index based procedure originally developed for the hidden Markov chain models, whic…
Paper proposes a deep subspace clustering method using multi-level representations.
problem Deep subspace clustering of images.
method Convolutional autoencoders with multiple fully-connected layers for multi-level representations, loss minimization with iterative updates.
result The method outperforms state-of-the-art methods on real-world datasets.
Sparse representations using learned dictionaries are being increasingly used with success in several data processing and machine learning applications. The availability of abundant training data necessitates the development of efficient, robust and provably good dictionary learning algorithms. Algorithmic stability an…
A deep model detects differentially expressed genes from single-cell RNA seq data.
problem Detecting differentially expressed genes from single-cell RNA sequencing data.
method Probabilistic model with neural network conditional distributions, variational inference, stochastic optimization.
result The model outperforms state-of-the-art methods for differential expression detection.
ARK improves knockoffs robustness to feature distribution misspecification.
problem Robustness of knockoffs inference to misspecified feature distributions.
method Coupling approximate knockoffs with model-X knockoffs to achieve FDR and FWER control.
result The approximate knockoffs procedure can control FDR and FWER asymptotically.
Efficiently estimates variable importance in prediction tasks using Shapley values.
problem Valid statistical inference on the importance of variables in prediction tasks.
method Randomly sampling feature subsets to estimate Shapley Population Variable Importance Measure (SPVIM) efficiently.
result The proposed estimator converges at an asymptotically optimal rate and can construct valid confidence intervals and hypothesis tests.
A novel procedure detects outliers in functional data using multiple testing.
problem Outlier detection in functional data.
method Multiple testing based on two-sample test on coefficients of functional data projected onto orthonormal bases.
result Selected coefficients as features for outlier detection using Local Outlier Factor.
A clustering method for multivariate populations with similar dependence structures.
problem Grouping populations with similar dependence structures.
method Orthogonal projection coefficients of density copulas estimated from populations.
result Clusters of populations with similar dependence structures.
Graph products inherit Morse local-to-global property from their components.
problem Generalizing local-to-global property to graph products of infinite groups.
method Generalizing maximization procedure for relatively hierarchically hyperbolic groups and showing stable embeddings.
result Graph products of infinite Morse local-to-global groups have the Morse local-to-global property.
We present two Bayesian procedures to infer the interactions and external currents in an assembly of stochastic integrate-and-fire neurons from the recording of their spiking activity. The first procedure is based on the exact calculation of the most likely time courses of the neuron membrane potentials conditioned by …
The paper develops methods for causal function estimation and inference with multiway clustered data.
problem Estimation and inference for causal functions under multiway clustering.
method Two-step procedure using machine learning for nuisance parameters and projection onto basis functions.
result Rejects the null hypothesis of uniformly zero effects and reveals heterogeneous treatment effects.
Rogue-Gym tests RL agents' generalization in procedurally generated dungeons.
problem Overfitting in RL agents in different environments.
method Proposes Rogue-Gym, a roguelike game for evaluating RL generalization.
result Some RL enhancements fail to improve generalization in Rogue-Gym.