Imitation learning methods are used to infer a policy in a Markov decision process from a dataset of expert demonstrations by minimizing a divergence measure between the empirical state occupancy measures of the expert and the policy.
We propose a framework that utilizes interpretable disentangled representations for downstream-task prediction.
With the rise of large-scale models trained on broad data, in-context learning has become a new learning paradigm that has demonstrated significant potential in natural language processing and computer vision tasks.
To overcome this, we formulate a Pareto optimization problem in which we simultaneously optimize for reward and OOD detection performance.
In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning.
Robustness to adversarial perturbations has been explored in many areas of computer vision.
To address this problem, we postulate that real-world distributions are composed of latent Invariant Elementary Distributions (I. E. D) across different domains.
Inverse reinforcement learning methods aim to retrieve the reward function of a Markov decision process based on a dataset of expert demonstrations.
In clinical practice, regions of interest in medical imaging often need to be identified through a process of precise image segmentation.
We show that augmenting the decoder of a hierarchical VAE by spatial dependency layers considerably improves density estimation over baseline convolutional architectures and the state-of-the-art among the models within the same class.
The result follows from two main technical points: (i) the connection established between the MLE and the MMSE, using the first and second-moment methods in the constrained signal space, (ii) a recovery regime for the MMSE stricter than the simple error vanishing characterization given in the standard AoN, that is here proved as a general result.
In this work, we consider the problem of recovery a planted $k$-densest sub-hypergraph on $d$-uniform hypergraphs.
The segmentation of the mitral valve annulus and leaflets specifies a crucial first step to establish a machine learning pipeline that can support physicians in performing multiple tasks, e. g.\ diagnosis of mitral valve diseases, surgical planning, and intraoperative procedures.
We start by a thorough characterization of the class of continuous submodular functions, and show that continuous submodularity is equivalent to a weak version of the diminishing returns (DR) property.
Submodular functions have been studied extensively in machine learning and data mining.
Despite federated multi-task learning being shown to be an effective paradigm for real-world datasets, it has been applied only on convex models.
Sequential data often originates from diverse domains across which statistical regularities and domain specifics exist.
To learn robust cross-environment descriptions of sequences we introduce disentangled state space models (DSSM).
Estimating what would be an individual's potential response to varying levels of exposure to a treatment is of high practical relevance for several important fields, such as healthcare, economics and public policy.
Parameter identification and comparison of dynamical systems is a challenging task in many fields.
That is why, despite the high computational cost, numerical integration is still the gold standard in many applications.
Our guarantees are characterized by a combination of the (generalized) curvature $\alpha$ and the submodularity ratio $\gamma$.
We show that the regret of Ada-LR is close to the regret of full-matrix AdaGrad which can have an up-to exponentially smaller dependence on the dimension than the diagonal variant.
The essence of gradient matching is to model the prior over state variables as a Gaussian process which implies that the joint distribution given the ODE's and GP kernels is also Gaussian distributed.
Gaussian processes are powerful, yet analytically tractable models for supervised learning.
Submodular continuous functions are a category of (generally) non-convex/non-concave functions with a wide spectrum of applications.
Accurate and robust cell nuclei classification is the cornerstone for a wider range of tasks in digital and Computational Pathology.
This more efficient use of training data results in better performance on popular benchmark datasets with smaller number of parameters when comparing to standard convolutional neural networks with dataset augmentation and to other baselines.
Many Computer Vision problems arise from information processing of data sources with nuisance variances like scale, orientation, contrast, perspective foreshortening or - in medical imaging - staining and local warping.
Subsampling methods have been recently proposed to speed up least squares estimation in large scale settings.
Random views are justified by recent theoretical and empirical work showing that regression with random features closely approximates kernel regression, implying that random views can be expected to contain accurate estimators.