TurboSVM-FL: Boosting Federated Learning through SVM Aggregation for Lazy...
Federated learning is a distributed collaborative machine learning paradigm that has gained strong momentum in recent years. In federated learning, a central server periodically coordinates models with...
View ArticleNoninvasive Acute Compartment Syndrome Diagnosis Using Random Forest Machine...
Acute compartment syndrome (ACS) is an orthopedic emergency, caused by elevated pressure within a muscle compartment, that leads to permanent tissue damage and eventually death. Diagnosis of ACS relies...
View ArticlePreparing Lessons for Progressive Training on Language Models
The rapid progress of Transformers in artificial intelligence has come at the cost of increased resource consumption and greenhouse gas emissions due to growing model sizes. Prior work suggests using...
View ArticleX Hacking: The Threat of Misguided AutoML
Explainable AI (XAI) and interpretable machine learning methods help to build trust in model predictions and derived insights, yet also present a perverse incentive for analysts to manipulate XAI...
View ArticleBeyond Extraction: Contextualising Tabular Data for Efficient Summarisation...
The conventional use of the Retrieval-Augmented Generation (RAG) architecture has proven effective for retrieving information from diverse documents. However, challenges arise in handling complex table...
View ArticleKernel-U-Net: Symmetric and Hierarchical Architecture for Multivariate Time...
Time series forecasting task predicts future trends based on historical information. Transformer-based U-Net architectures, despite their success in medical image segmentation, have limitations in both...
View ArticleOn Learning for Ambiguous Chance Constrained Problems
We study chance constrained optimization problems $\min_x f(x)$ s.t. $P(\left\{ \theta: g(x,\theta)\le 0 \right\})\ge 1-\epsilon$ where $\epsilon\in (0,1)$ is the violation probability, when the...
View ArticleIn-Context Reinforcement Learning for Variable Action Spaces
Recently, it has been shown that transformers pre-trained on diverse datasets with multi-episode contexts can generalize to new reinforcement learning tasks in-context. A key limitation of previously...
View ArticleParameterized Projected Bellman Operator
Approximate value iteration (AVI) is a family of algorithms for reinforcement learning (RL) that aims to obtain an approximation of the optimal value function. Generally, AVI algorithms implement an...
View ArticleFedSSA: Semantic Similarity-based Aggregation for Efficient...
Federated learning (FL) is a privacy-preserving collaboratively machine learning paradigm. Traditional FL requires all data owners (a.k.a. FL clients) to train the same local model. This design is not...
View ArticleLearning the Causal Structure of Networked Dynamical Systems under Latent...
This paper considers learning the hidden causal network of a linear networked dynamical system (NDS) from the time series data at some of its nodes -- partial observability. The dynamics of the NDS are...
View ArticleWhat Causes Polysemanticity? An Alternative Origin Story of Mixed Selectivity...
Polysemantic neurons -- neurons that activate for a set of unrelated features -- have been seen as a significant obstacle towards interpretability of task-optimized deep networks, with implications for...
View ArticleClass Distribution Shifts in Zero-Shot Learning: Learning Robust Representations
Class distribution shifts are particularly challenging for zero-shot classifiers, which rely on representations learned from training classes but are deployed on new, unseen ones. Common causes for...
View ArticleOn robust overfitting: adversarial training induced distribution matters
Adversarial training may be regarded as standard training with a modified loss function. But its generalization error appears much larger than standard training under standard loss. This phenomenon,...
View ArticleDeciphering and integrating invariants for neural operator learning with...
Neural operators have been explored as surrogate models for simulating physical systems to overcome the limitations of traditional partial differential equation (PDE) solvers. However, most existing...
View ArticleLinear Log-Normal Attention with Unbiased Concentration
Transformer models have achieved remarkable results in a wide range of applications. However, their scalability is hampered by the quadratic time and memory complexity of the self-attention mechanism...
View ArticleEfficient Reinforcement Learning from Partial Observability
In most real-world reinforcement learning applications, state information is only partially observable, which breaks the Markov decision process assumption and leads to inferior performance for...
View ArticleDeliverAI: Reinforcement Learning Based Distributed Path-Sharing Network for...
Delivery of items from the producer to the consumer has experienced significant growth over the past decade and has been greatly fueled by the recent pandemic. Amazon Fresh, Shopify, UberEats,...
View ArticleImproving Robustness via Tilted Exponential Layer: A Communication-Theoretic...
State-of-the-art techniques for enhancing robustness of deep networks mostly rely on empirical risk minimization with suitable data augmentation. In this paper, we propose a complementary approach...
View ArticleCOSTAR: Improved Temporal Counterfactual Estimation with Self-Supervised...
Estimation of temporal counterfactual outcomes from observed history is crucial for decision-making in many domains such as healthcare and e-commerce, particularly when randomized controlled trials...
View Article