Epsilon*: Privacy Metric for Machine Learning Models
We introduce Epsilon*, a new privacy metric for measuring the privacy risk of a single model instance prior to, during, or after deployment of privacy mitigation strategies. The metric requires only...
View ArticleSafe Reinforcement Learning as Wasserstein Variational Inference: Formal...
Reinforcement learning can provide effective reasoning for sequential decision-making problems with variable dynamics. Such reasoning in practical implementation, however, poses a persistent challenge...
View ArticleSet Learning for Accurate and Calibrated Models
Model overconfidence and poor calibration are common in machine learning and difficult to account for when applying standard empirical risk minimization. In this work, we propose a novel method to...
View ArticleMachine Learning needs Better Randomness Standards: Randomised Smoothing and...
Randomness supports many critical functions in the field of machine learning (ML) including optimisation, data selection, privacy, and security. ML systems outsource the task of generating or...
View ArticleBoosting Multitask Learning on Graphs through Higher-Order Task Affinities
Predicting node labels on a given graph is a widely studied problem with many applications, including community detection and molecular graph prediction. This paper considers predicting multiple node...
View ArticleCooperative Multi-Agent Learning for Navigation via Structured State Abstraction
Cooperative multi-agent reinforcement learning (MARL) for navigation enables agents to cooperate to achieve their navigation goals. Using emergent communication, agents learn a communication protocol...
View ArticleExact Mean Square Linear Stability Analysis for SGD
The dynamical stability of optimization methods at the vicinity of minima of the loss has recently attracted significant attention. For gradient descent (GD), stable convergence is possible only to...
View ArticleBring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The...
Robust Markov Decision Processes (RMDPs) provide a framework for sequential decision-making that is robust to perturbations on the transition kernel. However, current RMDP methods are often limited to...
View ArticleRevising deep learning methods in parking lot occupancy detection
Parking guidance systems have recently become a popular trend as a part of the smart cities' paradigm of development. The crucial part of such systems is the algorithm allowing drivers to search for...
View ArticleMESSY Estimation: Maximum-Entropy based Stochastic and Symbolic densitY...
We introduce MESSY estimation, a Maximum-Entropy based Stochastic and Symbolic densitY estimation method. The proposed approach recovers probability density functions symbolically from samples using...
View ArticleInitial Guessing Bias: How Untrained Networks Favor Some Classes
Understanding and controlling biasing effects in neural networks is crucial for ensuring accurate and fair model performance. In the context of classification problems, we provide a theoretical...
View ArticleOn Convergence of Incremental Gradient for Non-Convex Smooth Functions
In machine learning and neural network optimization, algorithms like incremental gradient, and shuffle SGD are popular due to minimizing the number of cache misses and good practical convergence...
View ArticleBadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise...
View ArticleDropout Drops Double Descent
This study demonstrates that double descent can be mitigated by adding a dropout layer adjacent to the fully connected linear layer. The unexpected double-descent phenomenon garnered substantial...
View ArticleDiffusion Language Models Generation Can Be Halted Early
Diffusion Language models (DLMs) are a promising avenue for text generation due to their practical properties on tractable controllable generation. They also have the advantage of not having to predict...
View ArticleExploring the cloud of feature interaction scores in a Rashomon set
Interactions among features are central to understanding the behavior of machine learning models. Recent research has made significant strides in detecting and quantifying feature interactions in...
View ArticlePhysics Informed Token Transformer for Solving Partial Differential Equations
Solving Partial Differential Equations (PDEs) is the core of many fields of science and engineering. While classical approaches are often prohibitively slow, machine learning models often fail to...
View ArticleR2 Loss: Range Restriction Loss for Model Compression and Quantization
Model quantization and compression is widely used techniques to reduce usage of computing resource at inference time. While state-of-the-art works have been achieved reasonable accuracy with higher bit...
View ArticleScalable Neural Network Training over Distributed Graphs
Graph neural networks (GNNs) fuel diverse machine learning tasks involving graph-structured data, ranging from predicting protein structures to serving personalized recommendations. Real-world graph...
View ArticleProvable Robustness Against a Union of $\ell_0$ Adversarial Attacks
Sparse or $\ell_0$ adversarial attacks arbitrarily perturb an unknown subset of the features. $\ell_0$ robustness analysis is particularly well-suited for heterogeneous (tabular) data where features...
View Article