7103 papers
This paper proposes Hybrid Hierarchical RL (H^2RL), a two-stage framework that leverages logical option-based pretraining to inject symbolic structure into deep reinforcement learning agents, effectively mitigating reward misalignment and improving long-horizon decision-making while outperforming existing neural, symbolic, and neuro-symbolic baselines.
This paper introduces AllScAIP, a scalable, attention-based machine-learning interatomic potential that leverages all-to-all node attention to effectively capture long-range interactions and achieve state-of-the-art accuracy across diverse molecular and material systems without relying on explicit physics-based terms.
SCOPE introduces a plug-and-play framework for incremental few-shot 3D segmentation that enriches novel class prototypes by retrieving and fusing high-confidence pseudo-instances from unlabelled background regions, thereby achieving state-of-the-art performance on ScanNet and S3DIS while mitigating catastrophic forgetting without retraining the backbone.
The paper proposes BEVLM, a framework that bridges the gap between spatially consistent Bird's-Eye View representations and Large Language Models by distilling semantic knowledge, thereby significantly enhancing both cross-view reasoning accuracy and safety-critical end-to-end driving performance.
This paper proposes a Neyman-orthogonal estimator for linear multidimensional panel data with interactive fixed-effects that combines factor model methods with a weighted-within transformation to achieve parametric consistency and asymptotic normality, demonstrated through an application to beer demand elasticity.
This paper proposes two novel single-loop zeroth-order primal-dual algorithms, ZO-PDAPG and ZO-RMPDPG, that achieve state-of-the-art iteration complexity guarantees for solving nonconvex-(strongly) concave minimax problems with coupled linear constraints under both deterministic and stochastic settings.
This paper introduces Orthonormal Data Collaboration (ODC), a method that enforces orthonormal bases to transform the alignment challenge into a closed-form Orthogonal Procrustes problem, thereby achieving orthogonal concordance, significantly reducing computational complexity, and improving accuracy without compromising privacy or communication efficiency.
This paper proposes a novel multi-task subset selection framework that achieves localized distributional robustness by introducing a relative-entropy regularization term, which is proven equivalent to maximizing a monotone composition of submodular functions and can be efficiently solved via greedy algorithms, as validated by experiments on satellite sensor selection and image summarization.
This paper proposes a novel two-phase learning framework that distills privileged information from LKH-generated expert trajectories to enable a non-holonomic vehicle to solve Dubins Traveling Salesman Problems with Neighborhoods approximately 50 times faster than traditional methods while ensuring all task points are visited.
The paper introduces HEroBM, a deep equivariant graph neural network that utilizes a hierarchical, local-principle-based approach to achieve accurate, transferable, and universal backmapping from coarse-grained to all-atom molecular representations across diverse chemical systems.
This paper proposes an asymptotically optimal online learning and optimization algorithm for minimizing irreversible facility openings under a coverage target, demonstrating that a policy balancing initial limited exploration with subsequent rapid exploitation achieves sub-linear regret that converges exponentially fast to its infinite-horizon limit.
This paper introduces Parallel Split Learning with Global Sampling (GPSL), a server-driven scheme that fixes the global batch size and uses pooled-level proportions to draw local samples without replacement, thereby eliminating rounding bias, stabilizing optimization under non-IID data, and achieving centralized-like accuracy with negligible overhead.
This paper proposes a min-max formulation for Non-negative Matrix Factorization (NMF) to mitigate group bias, deriving specific optimization algorithms and demonstrating through experiments that while this approach can improve fairness, it may increase individual error, necessitating application-specific trade-off considerations.
This paper presents a comprehensive experimental study demonstrating that fairness-aware machine learning models achieve a superior balance between predictive accuracy and fairness compared to traditional classification models in the context of credit scoring.
This paper introduces Path Planning (P2), a novel inference sampling strategy for Masked Diffusion Models that decomposes generation into planning and denoising stages to enable iterative token refinement, thereby establishing a new expanded evidence lower bound and achieving state-of-the-art performance across diverse domains including protein sequences, RNA, math, storytelling, and code generation.
This paper demonstrates that training shallow neural networks with Lipschitz continuous activation functions to approximate smooth target functions suffers from the curse of dimensionality, as the population risk decays at a rate bounded by a power of time that depends inversely on the input dimension, regardless of whether the optimization is analyzed via empirical or population risk or through 2-Wasserstein gradient flow dynamics.
This paper extends entropy flow-based generalization bounds from specific noisy algorithms to all learning processes governed by time-homogeneous Markov dynamics by introducing a new exact entropy flow formula and linking generalization error to ergodic properties via modified logarithmic Sobolev inequalities.
This paper refutes the conjecture that sink equilibria are in one-to-one correspondence with the attractors of the replicator dynamic by presenting counterexamples based on "local sources," while establishing "pseudoconvexity" as a sufficient condition for this correspondence to hold in two-player games.
This paper proposes Field-Based Federated Learning (FBFL), a novel macroprogramming-driven approach that utilizes distributed spatial leader election and self-organizing hierarchical architectures to effectively address data heterogeneity and centralization bottlenecks, demonstrating superior performance over state-of-the-art methods like FedAvg, FedProx, and Scaffold in non-IID scenarios while maintaining resilience against server failures.
This paper introduces Clip21-SGD2M, a novel federated learning algorithm that combines clipping, heavy-ball momentum, and error feedback to achieve both optimal convergence rates for non-convex problems with heterogeneous data and near-optimal differential privacy guarantees without restrictive assumptions.