Enhances exploration in hierarchical networks using mutual information.
problem Limited exploration in hierarchical Deep Q-Networks.
method Adversarial Soft Actor-Critic with mutual information optimization.
result Improves hierarchical network exploration through mutual information maximization.
RLHC uses multiple critics at different levels to enhance RL performance.
problem Speed up RL learning and increase cumulative rewards in competition tasks.
method Introducing multiple cooperative critics at two levels of a hierarchy to provide global information.
result RLHC outperforms PPO in tennis and soccer competitions.
Curious hierarchical reinforcement learning improves learning performance.
problem Combining hierarchical abstraction and curiosity-driven exploration in reinforcement learning.
method Developed a method that combines hierarchical reinforcement learning with curiosity.
result Curiosity can more than double learning performance and success rates.
Global convergence proved for multi-agent LQRs with hierarchical actor-critic.
problem Challenges in understanding multi-agent reinforcement learning algorithms.
method Developed a hierarchical actor-critic algorithm for partially exchangeable agents.
result Global linear convergence to optimal policy proved.
Paper proposes a hierarchical approach for early anomaly detection in time series data for critical health events.
problem Early detection of critical health events in intensive care units.
method A layered learning architecture that breaks the problem into pre-conditional and event layers.
result The proposed method outperforms state-of-the-art approaches for critical health episode prediction.
Proposes a model for multi-agent reinforcement learning with hierarchical graph attention network.
problem Limited transferability of trained policies to new multi-agent tasks.
method Uses hierarchical graph attention network for representation learning and multi-agent actor-critic for policy learning.
result Demonstrates superior performance in mixed cooperative and competitive tasks compared to existing methods.
DAC combines actor-critic methods for learning options.
problem Learning hierarchical policies in reinforcement learning.
method Double Actor-Critic (DAC) architecture using two parallel augmented MDPs.
result DAC outperforms existing methods in robot simulation tasks.
MolHF generates complex molecules with hierarchical flow-based model.
problem Designing novel molecular structures with desired properties.
method MolHF is a hierarchical normalizing flow model that generates molecular graphs in a coarse-to-fine manner.
result MolHF achieves state-of-the-art performance in random generation and property optimization.
Language helps RL agents learn complex tasks by composing sub-skills.
problem Solving complex, temporally-extended tasks in RL.
method Using language as an abstraction to learn and reuse sub-skills.
result Agents can learn and solve diverse, temporally-extended tasks.
HSML tailors meta-learning knowledge to task clusters.
problem Handling task uncertainty and heterogeneity in meta-learning.
method Gradient-based HSML with hierarchical task clustering.
result HSML achieves state-of-the-art performance in few-shot learning.
Paper proposes a new method for predicting DER adoption with hierarchical guarantees.
problem Accurately predicting DER adoption in electric grids with uncertainty and spatial disparity.
method Multivariate Hawkes process for modeling DER adoption dynamics and split conformal prediction algorithm for hierarchical validity.
result Empirical evaluation shows superior predictive accuracy and uncertainty calibration compared to existing methods.
We identify 'critical windows' in diffusion models where specific features emerge, providing a theoretical framework.
problem Understanding narrow time intervals in diffusion models where specific features emerge.
method Developed a formal framework to study these critical windows, showing provable bounds for certain data types.
result Proved that critical windows can be bounded in terms of measures of separation for data from mixtures of log-concave densities.
Hybrid actor-critic learns in complex action spaces.
problem Learning in complex, structured action spaces.
method Parallel sub-actor networks and a critic network.
result Hybrid PPO outperforms previous methods in parameterized action spaces.
New A* algorithm improves hierarchical clustering quality.
problem Improving hierarchical clustering quality in large search spaces.
method Combining A* search with a trellis data structure.
result Achieves higher quality results than baselines in particle physics and other benchmarks.
Clustering is one of the most universal approaches for understanding complex data. A pivotal aspect of clustering analysis is quantitatively comparing clusterings; clustering comparison is the basis for many tasks such as clustering evaluation, consensus clustering, and tracking the temporal evolution of clusters. In p…
Unified coagent network theory with execution paths.
problem Hierarchical reinforcement learning exploration-exploitation trade-off.
method Formalized coagent networks, introduced execution paths, revisited coagent network theory.
result Shorter proof of policy gradient theorem, generalizable to asynchronous coagents.
Improved text summarization using neural semantic encoders with hierarchical structure.
problem Capturing long-term dependencies in text summarization.
method Proposed a novel hierarchical Neural Semantic Encoder (NSE) model augmented with lemma and PoS tags.
result Significantly outperformed state-of-the-art models in ROUGE metric.
Predicting keywords performance, such as number of impressions, click-through rate (CTR), conversion rate (CVR), revenue per click (RPC), and cost per click (CPC), is critical for sponsored search in the online advertising industry. An interesting phenomenon is that, despite the size of the overall data, the data are v…
Deep Learning can significantly benefit cancer proteomics and genomics. In this study, we attempt to determine a set of critical proteins that are associated with the FLT3-ITD mutation in newly-diagnosed acute myeloid leukemia patients. A Deep Learning network consisting of autoencoders forming a hierarchical model fro…
New VAE models reveal hierarchical visual cortex computations.
problem Capturing hierarchical visual cortex computations in generative models.
method Sparse coding hierarchical VAEs trained on natural images with varied generative and recognition components.
result Representations similar to those in visual cortex emerge under inductive biases.
New methods tackle complex inverse problems with scalable optimization-based MCMC.
problem Estimating high-dimensional model parameters and hyperparameters in nonlinear hierarchical statistical inverse problems.
method Optimization-based Markov chain Monte Carlo (MCMC) methods using RTO and pseudo-marginal MCMC.
result Efficient sampling tools for hierarchical Bayesian inversion with robust performance to model parameter dimensions.
The paper introduces structured variational families to improve scalability in black-box variational inference.
problem Scalability issues in black-box variational inference, especially for large datasets and hierarchical models.
method Developed structured variational families that achieve better iteration complexity of O(N) compared to full-rank families.
result Structured variational families can achieve better scaling with respect to dataset size N, improving iteration complexity from O(N^2) to O(N).
Three-layer networks learn complex hierarchical polynomials of multiple nonlinear features.
problem Understanding how neural networks learn hierarchical features of multiple nonlinear inputs.
method Examine a broad class of functions using three-layer neural networks, showing complete recovery and efficient learning.
result Three-layer neural networks trained via gradient descent can learn hierarchical polynomials of multiple nonlinear features efficiently.
Change detection (CD) in time series data is a critical problem as it reveal changes in the underlying generative processes driving the time series. Despite having received significant attention, one important unexplored aspect is how to efficiently utilize additional correlated information to improve the detection and…
Improves flu prediction by blending environment and population info.
problem Challenges in using data from one environment in another due to feature variability and population subgroup differences.
method Population-aware hierarchical Bayesian domain adaptation framework with multiple invariant components.
result Model improves flu prediction in new environments with unlabelled data.
FATHOM model improves sensor data analysis with attention and LSTM.
problem Scarcity of training data from multiple sensors.
method Federated multi-task hierarchical attention model (FATHOM) with attention mechanism and LSTM.
result FATHOM outperforms baselines in sensor data classification and regression.
Locally-verifiable conditions ensure exactness of spline discrete de Rham complex.
problem Ensuring cohomological equivalence of spline discrete complex to continuous de Rham complex.
method Theoretical analysis and locally-verifiable sufficient conditions for exactness.
result Locally-verifiable conditions guarantee exactness of hierarchical B-spline discrete de Rham complex.
New algorithms improve learning of long-term actions in reinforcement learning.
problem Violation of parameter independence assumption in deep function approximation.
method Reconsidered option-critic and hierarchical option-critic training for deep settings.
result Significantly improved stability and faster convergence in Atari games.
The recently proposed option-critic architecture Bacon et al. provide a stochastic policy gradient approach to hierarchical reinforcement learning. Specifically, they provide a way to estimate the gradient of the expected discounted return with respect to parameters that define a finite number of temporally extended ac…
Hierarchical temporal memory (HTM) is an emerging machine learning algorithm, with the potential to provide a means to perform predictions on spatiotemporal data. The algorithm, inspired by the neocortex, currently does not have a comprehensive mathematical framework. This work brings together all aspects of the spatia…
Study uses healthcare claims data to identify Covid-19 risk factors without prior selection.
problem Identify risk factors for severe Covid-19 cases.
method Fine-grained hierarchical information from medical classification systems used to analyze over 33,000 covariates.
result Method has better predictive ability than pre-specified morbidity groups.
SmallML predicts customer churn for SMEs with small data, improving accuracy by 24.2 points.
problem AI exclusion of SMEs due to data scale mismatch.
method Bayesian transfer learning with hierarchical pooling and conformal prediction.
result 96.7% AUC on 100 obs SMEs, 24.2 point improvement over logistic regression.
New model detects communities in multiplex networks, accounting for layer dependencies.
problem Detecting communities in multiplex networks with layer-specific dependencies.
method Hierarchical Bayesian model with a hierarchical Dirichlet prior and slice sampler.
result Model automatically picks the number of communities at each layer, outperforming single-layer alternatives.
Although shill bidding is a common auction fraud, it is however very tough to detect. Due to the unavailability and lack of training data, in this study, we build a high-quality labeled shill bidding dataset based on recently collected auctions from eBay. Labeling shill biding instances with multidimensional features i…
New method estimates and samples high-dimensional probability distributions avoiding optimization and approximation curse.
problem Estimating high-dimensional probability distributions from data samples.
method Hierarchic probability flow from coarse to fine scales, defined by conditional probabilities across scales.
result Sampling hierarchic models avoids critical slowing down at phase transitions and generates turbulence and dark matter images.
Paper resolves ambiguity in non-convex bilevel optimization problems.
problem Ambiguity in bilevel optimization with non-convex lower-level objectives.
method Introduces selection maps to define critical points and resolves ambiguity.
result Validates new analytical tools in Morse theory for implicit differentiation.
CPGAs converge to locally optimal policies for coagent networks.
problem Training stochastic neural networks using reinforcement learning.
method Proved convergence of CPGAs and extended prior theory to asynchronous and recurrent networks.
result CPGAs converge to locally optimal policies for coagent networks, including asynchronous and recurrent networks.
A method clusters genes in large gene regulatory networks using semi-supervised hierarchical clustering.
problem Challenging task of identifying interaction clusters in large gene regulatory networks due to data noise and inconsistency.
method SHC-DC: a semi-supervised hierarchical clustering method using deconvolved correlation matrix.
result SHC-DC discovers interaction modules enriched in various signal pathways, validating sleep's impact on interleukin levels and related pathways.
To train good supervised and semi-supervised object classifiers, it is critical that we not waste the time of the human experts who are providing the training labels. Existing active learning strategies can have uneven performance, being efficient on some datasets but wasteful on others, or inconsistent just between ru…
Graded Transformers embed algebraic structure in neural networks through graded transformations.
problem Efficiently modeling hierarchical and structured data in neural networks.
method Introduces Linearly Graded Transformer (LGT) and Exponentially Graded Transformer (EGT) with graded scaling operators.
result Establishes rigorous guarantees and improved efficiency for structured data.
New test improves clustering accuracy for Gaussian mixtures.
problem Improving clustering accuracy for Gaussian mixtures.
method Relative fit test for Gaussian Mixture Models.
result New test provides provable error control and higher power.
AG-RL uses action grammars to improve reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Integrates action grammars into reinforcement learning algorithms to enhance performance.
result Significant improvement in performance across multiple Atari games.
TreeHFD algorithm explains tree ensemble models through hierarchical orthogonality.
problem Difficulty in explaining black-box tree ensemble models.
method TreeHFD algorithm using hierarchical orthogonality constraints.
result TreeHFD estimates Hoeffding decomposition from data samples.
Contrastive learning properties studied, including feature suppression and hierarchical learning.
problem Feature suppression and hierarchical learning in contrastive learning.
method Generalized contrastive loss, instance-based contrastive learning, explicit and controllable competing features.
result Contrastive learning can suppress and prevent the learning of competing features.
This paper optimizes portfolios using HRP and CLA algorithms on NIFTY 50 stocks.
problem Designing an optimal stock portfolio with accurate forecasting of future returns and risks.
method Uses hierarchical risk parity and critical line algorithms on NIFTY 50 stocks.
result Hierarchical risk parity algorithm outperformed the critical line algorithm on test data.
New method uses LLMs to generate detailed scientific hypotheses.
problem Generating detailed, actionable scientific hypotheses from coarse initial directions.
method Hierarchical search method that incrementally adds details to hypotheses.
result Hierarchical search method consistently outperforms strong baselines on expert-annotated hypotheses.
Improves RL planning by proposing sub-goals hierarchically.
problem Sequential planning assumption in RL.
method Divide-and-Conquer Monte Carlo Tree Search (DC-MCTS).
result Improves navigation and control tasks.
New method automates asymmetric choice for better skill transfer in reinforcement learning.
problem Improving sample efficiency and transferability of reinforcement learning agents.
method Attentive Priors for Expressive and Transferable Skills (APES) using hierarchical KL-regularization.
result APES automates asymmetric choice, leading to better skill transfer across sequential tasks.