Bayesian MAML outperforms MAML in meta learning tasks with theoretical guarantees.
problem Theoretical understanding of Bayesian MAML's superiority over MAML.
method Comparison of meta test risks between Bayesian MAML and MAML in meta linear regression.
result Bayesian MAML has provably lower meta test risks than MAML in both distribution agnostic and linear centroid cases.
Meta-learning method improves PU classification performance.
problem Improving binary classifiers from PU data in unseen tasks.
method Adapts model to PU data using related tasks and neural networks.
result Proposed method outperforms existing methods on synthetic and real-world datasets.
Meta-learning improves predictions with generalized ridge regression in high-dimensional settings.
problem Improving meta-learning performance in high-dimensional settings.
method Generalized ridge regression applied to high-dimensional multivariate random-effects linear models.
result Optimal predictive risk achieved when using the inverse of the covariance matrix of random coefficients.
We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential prediction algorithms. Our approach enables the task-similarity to be learned adapti…
The paper proves how Transformers learn from context and generalize well.
problem Understanding how Transformers generalize from diverse tasks.
method Developed a statistical theory for in-context learning, separating risk into Bayes Gap and Posterior Variance.
result The Posterior Variance is task-independent, and the Bayes Gap decreases with more in-context examples.
In recent years, increasingly augmentation of health data, such as patient Electronic Health Records (EHR), are becoming readily available. This provides an unprecedented opportunity for knowledge discovery and data mining algorithms to dig insights from them, which can, later on, be helpful to the improvement of the q…
Few-shot classification is the task of predicting the category of an example from a set of few labeled examples. The number of labeled examples per category is called the number of shots (or shot number). Recent works tackle this task through meta-learning, where a meta-learner extracts information from observed tasks …
Meta two-sample testing uses auxiliary data to quickly find powerful tests from limited samples.
problem Challenges in identifying powerful kernels for distinguishing complex distributions with limited data.
method Introduces meta two-sample testing (M2ST) to leverage abundant auxiliary data on related tasks.
result Proposed algorithms improve over baselines and identify powerful tests from scarce observations.
Meta-analysis finds people value insurance for low-probability risks more than expected.
problem Low-probability risks insurance demand is lower than expected.
method Conducted a meta-analysis of contingent valuation studies.
result Average stated willingness to pay (WTP) for insurance is 87% of expected losses.
Publication bias skews asset pricing research findings.
problem Bias in sharing and publishing research findings.
method Meta-studies and empirical Bayes corrections.
result Publication bias effects are minimal and not dominant.
In this work we study generalization of neural networks in gradient-based meta-learning by analyzing various properties of the objective landscapes. We experimentally demonstrate that as meta-training progresses, the meta-test solutions, obtained after adapting the meta-train solution of the model, to new tasks via few…
Meta-learning bounds derived using PAC-Bayes theory for improved generalization.
problem Uncertainty in generalization performance for meta-learning with new tasks.
method PAC-Bayes relative entropy bounds and empirical risk minimization (ERM) method.
result Competitive generalization performance and rapid convergence with data-dependent prior.
Paper proposes a method to evaluate SME credit risk using meta paths.
problem Evaluate credit risk of small and medium-sized enterprises with limited data.
method Exploits the representative power of information networks and meta paths to infer SME financial status.
result Meta path feature effectively identifies SMEs with credit risks.
MPM uses machine learning to switch between two portfolio strategies for better risk management.
problem Adaptive portfolio strategy selection for improved risk management.
method XGBoost learns to switch between HRP and NRP strategies.
result MPM outperforms both HRP and NRP in risk-reward profile and interpretability.
A machine learning model that generalizes well should obtain low errors on unseen test examples. Thus, if we know how to optimally perturb training examples to account for test examples, we may achieve better generalization performance. However, obtaining such perturbation is not possible in standard machine learning f…
New method improves meta-reinforcement learning efficiency.
problem Sample inefficiency in meta-reinforcement learning.
method Hindsight Foresight Relabeling (HFR) method.
result HFR improves performance on various meta-reinforcement learning tasks.
A new meta-learning framework that assigns weights to source tasks based on target samples.
problem Learning initialization for target tasks with limited labeled examples.
method A general framework that assigns weights to the loss of different source tasks, which can depend on the target samples. Provides upper bounds and develops a learning algorithm based on minimizing the error bound with respect to an empirical IPM.
result Empirically, the weighted meta-learning algorithm finds better initializations than uniformly-weighted meta-learning algorithms.
New method for incremental meta-learning reduces forgetting and improves performance.
problem Incremental meta-learning for few-shot classification tasks.
method Indirect Discriminant Alignment (IDA) with incremental updates.
result Incremental learning reduces forgetting and improves performance.
Meta-learning is a promising strategy for learning to efficiently learn within new tasks, using data gathered from a distribution of tasks. However, the meta-learning literature thus far has focused on the task segmented setting, where at train-time, offline data is assumed to be split according to the underlying task,…
Meta-learning reformulated as Bayesian risk minimization.
problem Learning models to quickly adapt to new tasks from small datasets.
method Formalized meta-learning as Bayesian risk minimization, using a probabilistic framework to compute predictive distributions from posterior distributions of latent variables conditioned on contextual datasets.
result A novel Gaussian approximation for the posterior distribution that converges to maximum likelihood estimates and outperforms Neural Process on benchmark datasets.
Ensembles are popular methods for solving practical supervised learning problems. They reduce the risk of having underperforming models in production-grade software. Although critical, methods for learning heterogeneous regression ensembles have not been proposed at large scale, whereas in classical ML literature, stac…
Meta-learning framework for credit risk assessment of SMEs, aligning financial statement dates with evaluation dates.
problem Temporal misalignment of credit scoring models leading to bias and inconsistent predictions.
method Two-step temporal decomposition: static model for annual PDs, dynamic model for monthly PDs; stacking architecture to aggregate multiple models.
result Framework effectively captures credit risk evolution over time, improving temporal consistency and predictive stability.
We extend first-order model agnostic meta-learning algorithms (including FOMAML and Reptile) to image segmentation, present a novel neural network architecture built for fast learning which we call EfficientLab, and leverage a formal definition of the test error of meta-learning algorithms to decrease error on out of d…
Risk Advisor predicts and mitigates ML deployment failures.
problem Predicting and mitigating test-time failure risks of ML systems.
method Post-hoc meta-learner for estimating failure risks and uncertainties.
result Reliably predicts deployment-time failure risks across various ML models.
We study 'meta-dependence' in conditional independence tests across different empirical distributions.
problem Understanding the breakdown of conditional independence properties in finite data.
method Geometric intuition and information projections to measure meta-dependence between conditional independences.
result We provide a measure of meta-dependence that consolidates findings across synthetic and real-world data.
This paper bounds meta-generalization gap using information theory.
problem Improving sample efficiency for new tasks in meta-learning.
method Information-theoretic upper bounds on meta-generalization gap for two meta-learning classes.
result Novel ITMI bounds for noisy iterative algorithms.
A major challenge in reinforcement learning (RL) is the design of agents that are able to generalize across tasks that share common dynamics. A viable solution is meta-reinforcement learning, which identifies common structures among past tasks to be then generalized to new tasks (meta-test). In meta-training, the RL ag…
Dynamic ensemble selection (DES) techniques work by estimating the level of competence of each classifier from a pool of classifiers. Only the most competent ones are selected to classify a given test sample. Hence, the key issue in DES is the criterion used to estimate the level of competence of the classifiers in pre…
A tensor model for meta-learning adapts to task-specific features.
problem Learning shared representations for diverse tasks without task-specific observable information.
method Modeling meta-parameters as an order-3 tensor, estimating through tensor regression and method of moments.
result Tensor-based approach improves meta-learning performance with fewer samples.
Paper introduces Balanced Meta-Softmax for better long-tailed visual recognition.
problem Long-tailed distribution mismatch between training and testing data.
method Balanced Meta-Softmax, an unbiased extension of Softmax, using a Meta Sampler.
result Balanced Meta-Softmax outperforms state-of-the-art solutions on visual recognition and instance segmentation.
The paper analyzes meta-learning in a Gaussian setting, providing bounds and matching algorithms.
problem Understanding how task distributions influence transfer risk in meta-learning.
method Fixed design linear regression with Gaussian noise, Gaussian task distribution, weighted biased regularized regression method.
result A novel weighted version of biased regularized regression method matches distribution-dependent lower bounds on transfer risk up to a constant factor.
When fitting Bayesian machine learning models on scarce data, the main challenge is to obtain suitable prior knowledge and encode it into the model. Recent advances in meta-learning offer powerful methods for extracting such prior knowledge from data acquired in related tasks. When it comes to meta-learning in Gaussian…
Meta-learner estimates heterogeneous DiD effects robustly.
problem Estimating heterogeneous treatment effects in panel data with DiD.
method Doubly robust meta-learner for CATT, using convex risk minimization and auxiliary models.
result Superior performance over existing methods in empirical tests.
AdMRL improves meta-reinforcement learning by minimizing worst-case sub-optimality gap.
problem Meta-reinforcement learning's sensitivity to task distribution shift.
method Model-based adversarial approach with minimax objective and alternating optimization.
result Efficacy in worst-case performance, generalization to out-of-distribution tasks, and sample efficiency.
Meta-models predict model hyperparameters for NDT experiments.
problem Non-destructive testing experiments are isolated; this work connects them.
method Bayesian multilevel approach, capturing inter-task relationships.
result Meta-models encode knowledge between and within tasks for transfer learning.
Meta-learning balances task-specific modeling and optimization complexity.
problem Balancing accurate task-specific modeling with ease of optimization in meta-learning.
method Theoretical and empirical analysis of trade-off between modeling and optimization in meta-learning.
result Explicit bounds on modeling and optimization errors for non-convex and linear regression problems.
The paper estimates personalized treatment effects in medical settings with competing risks.
problem Estimating treatment effectiveness for specific events in the presence of alternative event types.
method Meta-learners combining Cox regression or random survival forests for risk modeling and elastic net regression or random forests for direct CATE modeling.
result Compared meta-learners in multiple simulation settings, providing practical guidance for model selection.
This work sets theoretical limits on meta-learning performance.
problem Understanding the difficulty of adapting machine learning models to real-world data distributions.
method Information-theoretic lower bounds on convergence rates for meta-learning algorithms.
result Theoretical bounds on parameter estimation error for hierarchical Bayesian models of meta-learning.
New MAML variant prioritizes hardest tasks, improving robustness.
problem Meta-learning's focus on average performance, ignoring worst-case.
method Reformulate MAML to minimize max loss over observed tasks.
result Task-robust model performs well across various task distributions.
Adaptive-Step Graph Meta-Learner tackles few-shot graph classification with limited labeled data.
problem Few labeled graph data in bioinformatics and other applications.
method A novel framework combining a graph meta-learner and a step controller for robust and generalization.
result State-of-the-art results on several few-shot graph classification tasks.
GeneraLight improves traffic signal control models' generalization ability.
problem Overfitting and lack of generalization ability in RL TSC models.
method GeneraLight uses a meta-RL framework with a traffic flow generator based on GANs.
result GeneraLight significantly boosts generalization performance across different traffic flows.
Proposes a new probabilistic framework for domain generalization.
problem Learning predictors robust to unseen domain shifts.
method Quantile Risk Minimization (QRM) and Empirical QRM (EQRM) algorithms.
result Empirical QRM outperforms state-of-the-art baselines on various datasets.
Model interpretability is a requirement in many applications in which crucial decisions are made by users relying on a model's outputs. The recent movement for "algorithmic fairness" also stipulates explainability, and therefore interpretability of learning models. And yet the most successful contemporary Machine Learn…
New method optimises learning via surrogate PAC-Bayes bounds.
problem Computational intractability of optimising generalisation bounds.
method Iteratively optimising surrogate training objectives derived from PAC-Bayes bounds.
result Iteratively optimising surrogates implies optimising original generalisation bounds.
Unified framework improves meta-learning generalization bounds.
problem Limited sharpness of existing meta-generalization bounds.
method Unified information-theoretic derivation for single-step bounds.
result Unified bounds exhibit tighter scaling and computational advantages.
Investigates tight PAC-Bayes bounds for small datasets.
problem Tightening PAC-Bayes bounds for small data.
method Generic PAC-Bayes theorem, meta-learning, synthetic tasks.
result PAC-Bayes bounds are competitive with Chernoff bounds but not as tight.
MADOD meta-learns invariant features for OOD detection across unseen domains.
problem Simultaneous covariate and semantic shifts in real-world machine learning applications.
method Meta-learning and G-invariance to learn robust, domain-invariant features.
result Superior performance in semantic OOD detection across unseen domains.
Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks. The performance of meta-learning algorithms depe…