Posters

Federated online model selection needs collaboration only when clients have limited computing power; otherwise, independent learning suffices.

This paper provides novel algorithms and matching lower bounds for multi-armed bandits with expert advice and contextual linear bandits, resolving open questions and advancing theoretical understandin…

Fractal dimension, while showing promise, fails to consistently predict neural network generalization due to hyperparameter influence and adversarial initializations; prompting further research.

MIDAS: A novel training method improves language model reasoning by efficiently stacking middle layers, surprisingly boosting downstream task performance without increasing pretraining perplexity.

Standard initialization in neural networks negatively impacts generalization ability under Neural Tangent Kernel theory, contradicting real-world performance, urging the development of improved theore…

Graph Neural Networks (GNNs) struggle with heterophilic link prediction; this paper introduces formal definitions, theoretical analysis, improved designs, and real-world benchmarks to address this cha…

Meta-learning solves hybrid deep generative model unidentifiability!

Boosting GNN expressivity and generalization: Novel node individualization schemes lower sample complexity, improving substructure identification.

Tree-structured probabilistic circuits are surprisingly efficient: this paper proves a quasi-polynomial upper bound on their size, showing they’re almost as expressive as more complex DAG structures.

ERM’s efficiency in feature learning surprisingly remains high even with massive feature maps; its excess risk asymptotically matches an oracle procedure’s, implying potential for streamlined feature-…

This paper tackles the ‘curse of horizon’ in off-policy evaluation for partially observable Markov decision processes (POMDPs) by proposing novel coverage assumptions, enabling polynomial estimation e…

New active learning algorithm, Adaptive-Weight Sampling (AWS), achieves faster convergence with theoretical guarantees, improving data efficiency for machine learning.

This paper reveals surprising computational connections between algorithmic replicability and other learning paradigms, offering novel algorithms and demonstrating separations between replicability an…

This paper proposes a computationally efficient, differentially private best subset selection method for high-dimensional sparse linear regression, achieving both strong statistical utility and provab…

A novel algorithm, TIE, optimally teaches a family of linear behavior cloning learners, achieving instance-optimal teaching dimension while providing efficient approximation for larger action spaces.

Learning sparse functions efficiently with gradient methods is challenging; this paper introduces Differentiable Learning Queries (DLQ) to precisely characterize gradient query complexity, revealing s…

New polynomial-space algorithm for causal parameter identification in linear models vastly improves upon existing methods, showing that this crucial task is computationally hard.

Multi-modal contrastive learning surpasses single-modal by leveraging inter-modal correlations to improve feature learning and downstream task performance, as demonstrated through a novel theoretical …

Average-link hierarchical clustering gets a comprehensive evaluation using new criteria, showing it outperforms other methods when both cohesion and separability matter.

Public data boosts private AI accuracy even with extreme distribution shifts, improving private model training by up to 67% in three tasks. This is due to shared low-dimensional representations betwe…