Model-based RL learns Atari games faster with fewer interactions.
problem Efficiently learning Atari games with minimal interactions.
method Simulated Policy Learning (SimPLe) using video prediction models.
result SimPLe outperforms model-free methods in most Atari games with fewer interactions.
In human-in-the-loop machine learning, the user provides information beyond that in the training data. Many algorithms and user interfaces have been designed to optimize and facilitate this human--machine interaction; however, fewer studies have addressed the potential defects the designs can cause. Effective interacti…
Robo-advisors estimate clients' risk aversion using interactive questionnaires.
problem Estimating risk aversion of non-expert clients using adaptive questionnaires.
method Model risk aversion with cost functions and spectral risk measures. Use inverse reinforcement learning to design questions maximizing distinguishing power.
result Designing questions by maximizing distinguishing power achieves satisfactory accuracy in learning risk aversion with fewer than 50 questions.
Improved model-based reinforcement learning for interactive dialogue tasks reduces sample needs and improves performance.
problem Limited data and high sample cost in interactive dialogue systems.
method Model-based actor-critic approach with an environment model and planner.
result 70 times fewer samples required compared to baseline model-free algorithm, with 2x better asymptotic performance.
End-to-end Dyna-AIL combines planning and learning for faster convergence.
problem Efficient imitation learning with minimal interactions.
method Dyna-like framework integrating model-based planning and model-free learning.
result Our approach converges to optimal policies with fewer interactions.
Machine learning is used to approximate density functionals. For the model problem of the kinetic energy of non-interacting fermions in 1d, mean absolute errors below 1 kcal/mol on test densities similar to the training set are reached with fewer than 100 training densities. A predictor identifies if a test density is …
New neural networks model complex phenomena with fewer parameters.
problem Challenges in studying higher-order interactions in neural networks.
method Introducing curved neural networks using the maximum entropy principle.
result Curved neural networks accelerate memory retrieval and exhibit explosive phase transitions.
A core aspect of human intelligence is the ability to learn new tasks quickly and switch between them flexibly. Here, we describe a modular continual reinforcement learning paradigm inspired by these abilities. We first introduce a visual interaction environment that allows many types of tasks to be unified in a single…
To investigate the universality of the structure of interactions in different markets, we analyze the cross-correlation matrix C of stock price fluctuations in the National Stock Exchange (NSE) of India. We find that this emerging market exhibits strong correlations in the movement of stock prices compared to developed…
A new method for predicting with confidence for complex models.
problem Lack of reliable confidence in high-stake decision-making models.
method Developed a full-CP for sparse high-order interaction model using homotopy mining.
result SHIM achieves comparable accuracy to complex models and superior statistical power.
New method infers nonlinear Granger causality from time series data.
problem Inferring nonlinear Granger causality from time series data.
method Statistical Recurrent Units (SRUs) for modeling nonlinear interactions.
result The proposed economy-SRU model outperforms existing models in inferring Granger causality.
Develops methods for clustering hypergraphs with categorical edge labels.
problem Complex graph representations with multiple interaction types.
method Combinatorial objective function, polynomial-time algorithm for two types, linear programming relaxations for more types.
result Efficient algorithms for clustering hypergraphs with categorical edge labels.
Novel framework learns policies from noisy expert demonstrations.
problem Learning effective policies with noisy expert demonstrations.
method Adaptive learning framework that jointly interacts with the environment and expert demonstrations, assigning weights to filter out noisy demonstrations.
result The proposed approach learns robustly with noisy demonstrations and achieves higher performance in fewer iterations.
BART and MOTR-BART improve tree-based predictions with local linear models.
problem Non-linearity and high-order interactions in data.
method Bayesian Additive Regression Trees (BART) and Model Trees BART (MOTR-BART) using piecewise linear functions.
result MOTR-BART achieves equal or better performance with fewer trees than BART.
Improved algorithm for selecting a hypothesis locally privately with fewer queries.
problem Locally private hypothesis selection with minimal privacy-preserving queries.
method Introduces a Scheffé graph to reduce query complexity for hypothesis selection.
result Algorithm performs O~(k3/2) queries, improving on previous methods. Bayesian inference for inverse problems using mean-shift interacting particles
problem Bayesian inference for inverse problems
method Amortized mean-shift interacting particles
result Improves accuracy of Bayesian inference by reducing the number of samples needed
In online discussion communities, users can interact and share information and opinions on a wide variety of topics. However, some users may create multiple identities, or sockpuppets, and engage in undesired behavior by deceiving others or manipulating discussions. In this work, we study sockpuppetry across nine discu…
Improves generative Visual Dialog by asking diverse questions.
problem Generative Visual Dialog models degrade after a few rounds of interaction.
method Introduce a simple auxiliary objective to incentivize Qbot to ask diverse questions.
result Better dialog diversity, consistency, fluency, and detail with improved image relevance.
Deep Ptych uses generative models to reconstruct images with fewer samples.
problem Highly ill-posed and non-linear Fourier ptychography problem.
method Proposes a novel framework using generative models to regularize the Fourier ptychography problem.
result Deep Ptych outperforms existing techniques in image reconstruction quality and robustness.
DSVGD improves federated learning with fewer communication rounds.
problem Federated learning scalability and trustworthiness.
method Distributed Stein Variational Gradient Descent (DSVGD) for non-parametric Bayesian inference.
result DSVGD achieves comparable accuracy and scalability to other methods, with well-calibrated predictions.
The Turaev genus and dealternating number of a link are two invariants that measure how far away a link is from alternating. We determine the Turaev genus of a torus knot with five or fewer strands either exactly or up to an error of at most one. We also determine the dealternating number of a torus knot with five or f…
Hierarchical reinforcement learning (HRL) is a promising approach to extend traditional reinforcement learning (RL) methods to solve more complex tasks. Yet, the majority of current HRL methods require careful task-specific design and on-policy training, making them difficult to apply in real-world scenarios. In this p…
Improves reinforcement learning by combining off-policy data and exploration.
problem Data inefficiency and local optima in policy gradient methods.
method Combines off-policy data reuse, exploration, and deterministic policies with stochastic optimization.
result Successfully learns solutions using fewer interactions than standard methods.
New method identifies causal structures with fewer interventions.
problem Discovering causal structures from data.
method Active Intervention Targeting (AIT) method for learning causal DAGs.
result Significantly reduces the number of required interventions.
Networks capture pairwise interactions between entities and are frequently used in applications such as social networks, food networks, and protein interaction networks, to name a few. Communities, cohesive groups of nodes, often form in these applications, and identifying them gives insight into the overall organizati…
The concordance orders of many algebraic order two knots of ten or fewer crossings have been heretofore unknown. We use Casson-Gordon invariants and twisted Alexander polynomials to find that, in all but one case, these knots do not have concordance order two. We also find that a certain family of algebraic order two t…
We investigate the bi-orderability of two-bridge knot groups and the groups of knots with 12 or fewer crossings by applying recent theorems of Chiswell, Glass and Wilson. Amongst all knots with 12 or fewer crossings (of which there are 2977), previous theorems were only able to determine bi-orderability of 599 of the c…
Efficient NTF algorithm for large sparse tensors.
problem Sparse multi-dimensional data and limitations of existing NTF algorithms.
method Saturating Coordinate Descent with element selection based on Lipschitz continuity.
result Proposes a scalable NTF algorithm for large tensors.
Simplifies BCQ to match and outperform state-of-the-art in offline RL benchmarks.
problem Sample efficiency in offline reinforcement learning.
method Introduces EMaQ, a novel backup operator for offline RL.
result EMaQ matches and outperforms prior state-of-the-art in offline RL benchmarks.
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especiall…
S2cGAN uses fewer labels to train cGANs effectively.
problem Training conditional GANs requires expensive labelled data.
method Semi-supervised training with sparse labels and unsupervised data.
result S2cGAN learns conditional mapping with sparse labels and unconditional distribution with unsupervised data.
Hyperbolic knots are not common among prime knots.
problem Proportion of hyperbolic knots among prime knots does not reach 100% as knot complexity increases.
method Analyzing the proportion of hyperbolic knots and satellites among prime knots of increasing complexity.
result The proportion of hyperbolic knots does not converge to 100% as knot complexity increases.
New method uses fewer parameters to match state-of-the-art performance on multiple natural language tasks.
problem Efficiently adapting BERT for multiple tasks with fewer parameters.
method PALs (projected attention layers) for shared BERT model with task-specific parameters.
result Matches state-of-the-art performance on GLUE benchmark with 7 times fewer parameters.
Improved image generation with fewer labels.
problem Generating high-fidelity images with limited labeled data.
method Self- and semi-supervised learning techniques.
result Outperforms state-of-the-art models using 10-20% of labels.
Hybrid approach improves reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Approximate model from Model-Free RL, use Mean First Passage Times for reachability, design new algorithms.
result Hybrid approaches converge with fewer iterations and samples.
Tiny benchmarks reduce LLM evaluation costs by using fewer examples.
problem Expensive evaluation of LLMs with tens of thousands of examples.
method Developed evaluation tools and tiny versions of popular benchmarks.
result Accurately estimate LLM performance with just 100 curated examples.
Rarely switch policies to optimize treatment effects, reducing harmful changes.
problem Difficult to change policies frequently in real-world scenarios.
method Developed a conservative policy updating procedure for rarely-switching linear bandits.
result The procedure optimizes policies with fewer changes and fewer detrimental changes.
GGAN improves audio representation learning with fewer labels.
problem Learning representations for specific tasks from unlabelled data.
method Guided Generative Adversarial Neural Network (GGAN).
result GGAN learns better representations with fewer labelled data.
GEM-T generates synthetic tabular data by fitting moments, outperforming neural networks.
problem Generating synthetic tabular data from limited or sensitive real-world data.
method Generative Entropy Maximization (MaxEnt) for tables, capturing nth-order interactions.
result GEM-T matches or exceeds deep neural network approaches in 23 out of 34 datasets.
Polyhedra can mimic constant curvature surfaces, even with self-intersections.
problem Understanding curvature constraints in discrete vs. smooth settings.
method Constructive proof showing any surface can be realized as a polyhedral surface with uniform angular defect.
result Closed surfaces can be realized as polyhedral surfaces with constant angular defect.
FedConPE improves conversational recommender systems efficiency and privacy.
problem Efficiently eliciting user preferences in interactive systems with heterogeneous clients.
method Phase elimination-based federated conversational bandit algorithm with adaptive key term construction.
result Minimizes uncertainty across all dimensions in feature space and offers improved efficiency and privacy.
Study shows hyperbolic links are not common among prime links.
problem Understanding the prevalence of hyperbolic links among prime links.
method Analyzing satellite and prime non-split links of varying complexity.
result The proportion of hyperbolic links among all prime non-split links does not approach 1 as complexity increases.
ActiveLab improves classifier accuracy with fewer annotations by re-labeling.
problem Imperfect labels from multiple annotators in real-world data.
method ActiveLab automatically decides when to re-label examples for better classifier training.
result ActiveLab trains more accurate classifiers with fewer annotations.
BOBYQA optimizes deep networks with fewer queries than other methods.
problem Generating adversarial examples with fewer queries than non-model-based methods.
method Model-based derivative-free optimisation algorithm (BOBYQA).
result BOBYQA achieves state-of-the-art results with fewer queries than other methods.
Improved accuracy with fewer labels using MixMatch and active learning.
problem Achieving high accuracy with limited labeled data.
method Combining MixMatch and active learning techniques.
result Significant improvement in accuracy on CIFAR-10, CIFAR-100, and SVHN datasets.
Improved spectral clustering with fewer eigenvectors performs better.
problem Improving spectral clustering performance under weaker conditions.
method Tighter analysis and using fewer eigenvectors for embedding.
result Spectral clustering can produce better results with fewer eigenvectors.
Deep neural networks can approximate invariant/equivariant functions with fewer parameters.
problem Approximating functions that respect group symmetries with neural networks.
method Constructing deep neural networks with G-actions and G-equivariant/invariant affine transformations. result Deep neural networks can approximate G-invariant/equivariant functions with exponentially fewer parameters. Study assesses CNN model robustness to noise in low-cost CT scans.
problem Evaluate CNN model performance on noisy, artifact-prone low-cost CT images.
method Developed and tested a CNN model for head CT triage, varying tube current and projections.
result Model remains robust to reduced tube current and fewer projections, maintaining AUROC close to original.