The Rich and the Simple: On the Implicit Bias of Adam and SGD

The Cross-Modal Compositional Self-Distillation (CCSD) framework has been proposed to enhance brain tumor segmentation from multi-modal MRI scans. This method addresses the challenge of missing modalities in clinical settings, which can hinder the performance of deep learning models. By utilizing a shared-specific encoder-decoder architecture and two self-distillation strategies, CCSD aims to improve the robustness and accuracy of segmentation, ultimately aiding in clinical diagnosis and treatment planning.

Meta-SimGNN is a novel WiFi localization system that combines graph neural networks with meta-learning to enhance localization generalization and robustness. It addresses the limitations of existing deep learning-based localization methods, which primarily focus on environmental variations while neglecting the impact of device configuration changes. By introducing a fine-grained channel state information (CSI) graph construction scheme, Meta-SimGNN adapts to variations in the number of access points (APs) and improves usability in diverse scenarios.

The paper presents a Doppler Invariant Convolutional Neural Network (CNN) designed for automatic signal classification in radio spectrum monitoring. It addresses the limitations of existing deep learning models that rely on Doppler augmentation, which can hinder training efficiency and interpretability. The proposed architecture utilizes complex-valued layers and adaptive polyphase sampling to achieve frequency bin shift invariance, demonstrating consistent classification accuracy with and without random Doppler shifts using a synthetic dataset.

The paper presents SWAT-NN, a novel approach for optimizing neural networks by simultaneously training both their architecture and weights. Unlike traditional methods that rely on manual adjustments or discrete searches, SWAT-NN utilizes a multi-scale autoencoder to embed architectural and parametric information into a continuous latent space. This allows for efficient model optimization through gradient descent, incorporating penalties for sparsity and compactness to enhance model efficiency.

Saliency maps are essential for providing visual explanations in deep learning, yet there remains a significant lack of consensus regarding their purpose and alignment with user queries. This uncertainty complicates the evaluation and practical application of these explanation methods. To address this, a new taxonomy called Reference-Frame × Granularity (RFxG) is proposed, categorizing saliency explanations based on two axes: Reference-Frame and Granularity. This framework highlights limitations in existing evaluation metrics, emphasizing the need for a more comprehensive approach.

MicroEvoEval is introduced as a systematic evaluation framework aimed at predicting image-based microstructure evolution. This framework addresses critical gaps in the current methodologies, particularly the lack of standardized benchmarks for deep learning models in microstructure simulation. The study evaluates 14 different models across four MicroEvo tasks, focusing on both numerical accuracy and physical fidelity, thereby enhancing the reliability of microstructure predictions in materials design.

A new framework for reconstructing the microstructure of heterogeneous porous materials has been proposed, integrating neural networks with the sliced-Wasserstein metric. This approach enhances microstructure characterization and reconstruction, which are essential for modeling materials in engineering applications. By utilizing local pattern distribution and a controlled sampling strategy, the framework aims to improve the controllability and applicability of microstructure reconstruction, even with small sample sizes.

The study presents the first global convergence result for neural networks using a two-stage least squares (2SLS) approach in nonparametric instrumental variable regression (NPIV). By employing mean-field Langevin dynamics (MFLD) and addressing a bilevel optimization problem, the researchers introduce a novel first-order algorithm named F²BMLD. The findings include convergence and generalization bounds, highlighting a trade-off in the choice of Lagrange multipliers, and the method's effectiveness is validated through offline reinforcement learning experiments.