OCEAN infers online task identities from context variables.
problem Online task inference for compositional tasks with context adaptation.
method Variational inference framework OCEAN models global and local context variables in a joint latent space.
result OCEAN provides more effective task inference with sequential context adaptation.
Transformers infer tasks from context via two modes, geometrically shaped task vectors explain their behavior.
problem Understanding how transformers infer tasks from context and the geometric properties of task vectors.
method Synthetic setting to train small transformers, mathematical characterization of task-vector geometry and inference modes.
result Task-vector geometry shapes in-distribution and out-of-distribution behavior of transformers.
PPI uses proxy data to improve inference from limited labels across related tasks.
problem Statistical inference with limited labels across multiple related tasks.
method Prediction-powered inference framework that uses cross-task recalibration to improve power and accuracy.
result Cross-task recalibration can substantially reduce confidence interval widths when labels are scarce.
Selective inference improves multi-task neuroimaging analysis.
problem Improving predictive performance and modeling accuracy in neuroimaging studies.
method Proposes a framework for selective inference to jointly identify relevant covariates and conduct valid inference in a sparsity-inducing model.
result Selective inference yields tighter confidence intervals and more accurate signal recovery than single-task methods.
Aux-NAS uses auxiliary labels to improve primary task performance without extra inference cost.
problem Improving primary task performance using auxiliary labels without increasing inference cost.
method Architecture-based approach with a flexible asymmetric structure for primary and auxiliary tasks, using Neural Architecture Search (NAS) to evolve networks with only primary-to-auxiliary connections.
result Achieves improved performance on multiple tasks without increasing inference cost.
AGMs outperform EGMs in generalizing to unseen inference tasks.
problem Training graphical models for inference tasks not seen during training.
method Adversarial training of an ensemble of discrete graphical models.
result AGMs significantly outperform EGMs in generalization to unseen tasks.
New method improves crowdsourcing efficiency and inference of problem properties.
problem Crowdsourcing allocation strategies introduce bias, affecting inference of task difficulty and worker properties.
method Decision-Explicit Probability Sampling (DEPS) to infer problem properties accurately.
result DEPS outperforms baseline methods in inferring problem properties while maintaining efficiency gains.
MBML improves multi-task RL by inferring task identity from state-action pairs.
problem Multi-task batch reinforcement learning with unseen tasks.
method MBML uses triplet loss and relabeling to robustify task inference.
result Significantly faster convergence on unseen tasks compared to random initialization.
Paper proposes learnable topological features for efficient phylogenetic inference.
problem Finding appropriate topological structures for phylogenetic inference tasks requires significant design effort and domain expertise.
method Combines raw node features with graph neural networks to automatically adapt to different tasks.
result Demonstrates effectiveness and efficiency on simulated and real data phylogenetic inference tasks.
Crowdsourced labeling recovers task types with minimal queries.
problem Labeling tasks accurately with minimal queries.
method Worker clustering, skill estimation, weighted majority voting.
result Achieves any targeted recovery accuracy with minimum queries.
Novel framework for ML-assisted inference valid for any statistical task.
problem Limited validity of existing methods for post-prediction inference.
method Introduces PSPS framework for task-agnostic ML-assisted inference.
result Valid and efficient inference for arbitrary ML models.
New RL approach infers optimal policies via variational inference.
problem Manual design of reward functions for reinforcement learning.
method Variational inference for inferring policies achieving desired outcomes.
result Eliminates need for hand-crafted reward functions for diverse tasks.
Paper extends multi-task Gaussian Cox processes for heterogeneous tasks.
problem Modeling multiple heterogeneous correlated tasks jointly.
method Data augmentation and mean-field approximation for non-conjugate Bayesian inference.
result Demonstrates improved performance and inference on synthetic and real data.
Bayesian TAML balances meta-knowledge and task-specific learning for imbalanced tasks.
problem Meta-learning approaches struggle with varying instance and class numbers and distributional differences.
method Bayesian inference framework with variational inference to adaptively balance meta-knowledge and task-specific learning.
result Bayesian TAML significantly outperforms existing meta-learning approaches on imbalanced datasets.
Unified framework for simulation-based inference learns a single model for multiple tasks.
problem Simulation-based inference for multiple tasks with limited model retraining.
method Unified flow-matching generative model with query-aware masking distribution.
result Competitive performance on various inference tasks and real-world problems.
MTNPs jointly model multiple correlated tasks from various sources.
problem Naive NPs can only model a single stochastic process and infer tasks independently.
method MTNPs are a hierarchical extension of NPs that jointly infer tasks from multiple stochastic processes, considering inter-task correlation and handling incomplete data.
result MTNPs successfully model multiple tasks jointly, discovering and exploiting their correlations in various real-world data.
New model optimizes worker-task specialization for crowdsourcing.
problem Inferring correct labels from noisy answers across varying worker and task skills.
method Introduced a d-type specialization model to account for varying worker and task types, and proposed algorithms achieving optimal sample complexity. result Optimal label inference algorithms for crowdsourcing with unknown worker and task types.
Paper tackles high-order inference in structured prediction tasks.
problem Maximizing a score function on the space of labels in high-order Markov random fields.
method Generative model approach with two-stage convex optimization algorithm.
result Success in general high-order inference problems driven by hyperedge expansion properties.
Noise injection improves inference privacy in DNN models.
problem Malicious servers can infer sensitive attributes from input data.
method Adaptive Noise Injection (ANI) using a lightweight DNN on the client.
result Significant improvement in privacy (up to 48.5% degradation in sensitive-task accuracy with <1% degradation in primary accuracy).
Meta-learner infers subtask graph to adapt quickly to unknown tasks.
problem Adapting to unknown tasks with unknown subtask dependencies in few-shot RL.
method Meta-learner with Subtask Graph Inference (MSGI) and UCB-inspired intrinsic reward.
result Accurately infers latent task parameters and adapts more efficiently.
TripDecoder recovers metro routes and travel times from smart card data.
problem Recover unknown routes and travel times in metro systems.
method Decouples two inference tasks: travel time and route preference.
result TripDecoder improves accuracy and efficiency compared to competitors.
Efficiently infers neural architectures for unseen tasks.
problem High cost of neural architecture search.
method Gradient-based framework sharing information across tasks.
result Quick identification of good candidate architectures for new tasks.
This paper reviews causal inference methods for time series data.
problem Estimating treatment effects and identifying causal relations from time series data.
method Comprehensive review of approaches for treatment effect estimation and causal discovery.
result Provides a list of evaluation metrics and datasets for time series causal inference.
HuMaINs combines human and machine strengths for better inference tasks.
problem Improving inference performance through human-machine collaboration.
method Novel signal processing and machine learning solutions for HuMaINs architecture.
result HuMaINs achieves higher performance than either humans or machines individually.
Data science redefines causal inference from observational data, classifying tasks into description, prediction, and counterfactual prediction.
problem Widespread misunderstandings about data science's role in causal inference from observational data.
method Organizing data science tasks into three classes: Description, prediction, and counterfactual prediction (including causal inference).
result The necessity of subject-matter expert knowledge for causal analyses in data science.
Novel meta-RL strategy improves efficiency in learning novel tasks.
problem Efficiency in learning novel tasks using deep RL.
method Decomposes meta-RL into task-exploration, task-inference, and task-fulfillment; uses deep networks and a task encoder.
result Improves sample efficiency and mitigates meta-overfitting.
Active inference implemented for high-dimensional tasks shows efficient exploration and improved sample efficiency.
problem Achieving efficient exploration and learning in complex, uncertain environments.
method Active inference framework applied to high-dimensional tasks, with Bayesian evidence maximization.
result Order of magnitude increase in sample efficiency over model-free baselines.
Graph Neural Networks improve probabilistic inference in complex graphs.
problem Performing accurate inference in probabilistic graphical models with loops.
method Using Graph Neural Networks to learn and solve message-passing algorithms.
result GNNs outperform traditional belief propagation on loopy graphs.
Paper tackles hard attention training using variational inference.
problem Training hard attention models is difficult due to discrete latent variables.
method Uses variational inference methods (VIMCO, NVIL) and a novel adaptation.
result Method outperforms REINFORCE on phoneme recognition tasks.
Meta-learn Bayesian inference for task-specific BNNs using amortised inference.
problem Efficiently learning Bayesian inference for small-scale probabilistic meta-learning.
method Replace global inducing points with actual data to create a set of approximate likelihoods, train a meta-model to learn these parameters across related datasets.
result Meta-learned inference can be applied to task-specific BNNs, improving efficiency and scalability.
Paper proposes a method for learning and inferring movement using deep generative models.
problem Challenges in learning and inferring movement due to high dimensionality and varied environments.
method Formulates motion planning as learning on a directed graphic model and uses deep generative models.
result Flexibly incorporates task descriptors and context information for long-term planning.
SOFARI improves inference on multi-task learning latent factors.
problem Challenges in precise inference on multi-task learning latent factor matrices.
method High-dimensional manifold-based Neyman near-orthogonality inference on Stiefel manifold structure.
result Easy-to-use bias-corrected estimators for latent factor vectors and singular values with asymptotic normal distributions.
New method prevents invalid inference after causal discovery.
problem Invalid inference after causal discovery.
method Developed tools for valid post-causal-discovery inference.
result Our method provides reliable coverage while achieving more accurate causal discovery.
SDM Policy accelerates inference for robotic tasks while maintaining high action quality.
problem Prolonged inference times in diffusion-based policies for high-frequency control tasks.
method Two-stage optimization: score matching and distribution matching; dual-teacher mechanism.
result 6x inference speedup with state-of-the-art action quality.
Proposes a Bayesian federated learning method for diverse tasks.
problem Current federated learning approaches focus on homogeneous tasks, ignoring task diversity.
method Integrates multi-task learning with MOGP at the local level and federated learning at the global level.
result Demonstrates superior predictive performance and uncertainty calibration on diverse tasks.
Neurally-Guided Structure Inference combines search and data-driven methods for efficient, robust structure inference.
problem Combining the advantages of exhaustive search and data-driven methods for structure inference.
method Neurally-Guided Structure Inference (NG-SI) uses a neural network to guide hierarchical search over structures.
result NG-SI outperforms search-based and data-driven methods on probabilistic matrix decomposition and symbolic program parsing.
Proposes a new method for continual learning in neural networks.
problem Challenges in applying sequential Bayesian inference to neural networks.
method Sequential function-space variational inference.
result Neural networks trained with the proposed method achieve better predictive accuracy.
We solve varying-coefficient models with Gaussian process priors efficiently.
problem Learning varying relationships between input and output with additional task variables.
method Isotropic Gaussian process priors for varying-coefficient models, leading to efficient inference.
result Efficient inference for varying-coefficient models with Gaussian process priors.
VISR learns controllable features for fast task inference.
problem Generalizing behaviors beyond explicitly learned set for subsequent tasks.
method Combines Successor Features and Variational Inference.
result Achieves human-level performance on 14 Atari games.
A new method for multi-task learning infers task hierarchies from data.
problem Inferring predictive maps between multiple tasks in plant genetics.
method Task clustering for sparse linear regression models.
result Superior predictive models and genetic mapping from remote sensing data.
Simformer uses transformer models to perform flexible Bayesian inference.
problem Current simulation-based inference methods are inflexible and require fixed priors.
method Trains a probabilistic diffusion model with transformer architectures.
result Outperforms state-of-the-art methods on various benchmarks.
SoftCVI uses contrastive estimation to infer complex posteriors.
problem Estimating complex posteriors in Bayesian inference.
method Contrastive variational inference with self-generated soft labels.
result SoftCVI outperforms other variational approaches in stability and coverage.
Continuous-time flows unify inference and density estimation.
problem Efficient inference and robust density estimation for latent-variable models.
method Continuous-time flows (CTFs) as a diffusion-based framework for both tasks.
result CTFs achieve both inference and density estimation in a unified framework with theoretical guarantees.
Meta-RL algorithm improves sample efficiency and adaptability.
problem Challenges in meta-reinforcement learning, especially on-policy experience and task uncertainty.
method Develops an off-policy meta-RL algorithm that probabilistically infers task variables.
result Significantly outperforms prior algorithms in sample efficiency and asymptotic performance.
MetaVRF learns adaptive kernels for fast few-shot learning.
problem Few-shot learning with limited data.
method MetaVRF with latent variable model and variational inference.
result MetaVRF produces kernels with high representational power and fast adaptation.
CInA method uses attention to improve causal inference.
problem Challenges in causal inference, especially in complex tasks.
method CInA method utilizes self-supervised causal learning with multiple unlabeled datasets and transformer-type architecture.
result CInA effectively generalizes to out-of-distribution datasets and various real-world datasets.
CIfly simplifies causal inference tasks with linear-time reachability primitives.
problem Efficiently solving complex causal inference problems.
method Formalizes reachability as a core operation, builds on state-space graphs, and uses rule tables.
result CIfly algorithms run in linear time, outperforming existing methods.
Develops a scalable multi-task Gaussian process with neural embedding for improved performance.
problem High model complexity and limited model capability in multi-task Gaussian processes.
method Neural embedding of coregionalization, advanced variational inference, sparse approximation.
result Higher prediction quality and better generalization of the NSVLMC model.