no code implementations • 3 Feb 2025 • Minttu Alakuijala, Ya Gao, Georgy Ananov, Samuel Kaski, Pekka Marttinen, Alexander Ilin, Harri Valpola
As the general capabilities of artificial intelligence (AI) agents continue to evolve, their ability to learn to master multiple complex tasks through experience remains a key challenge.
no code implementations • 12 Dec 2024 • Hans Moen, Vishnu Raj, Andrius Vabalas, Markus Perola, Samuel Kaski, Andrea Ganna, Pekka Marttinen
However, instead of providing a single prediction about diagnoses that could occur in this forecast interval, our approach enable the model to provide continuous predictions at every time point up until, and conditioned on, the time of the forecast period.
no code implementations • 5 Nov 2024 • Sabina J. Sloman, Julien Martinelli, Samuel Kaski
PROMPT uses the same proxy information for two purposes: (i) estimation of effects specific to the target task, and (ii) construction of a robust reweighting of the source data for estimation of effects that transfer between tasks.
1 code implementation • 4 Nov 2024 • Daolang Huang, Yujia Guo, Luigi Acerbi, Samuel Kaski
Many critical decisions, such as personalized medical diagnoses and product pricing, are made based on insights gained from designing, observing, and analyzing a series of experiments.
no code implementations • 20 Oct 2024 • Paul E. Chang, Nasrulloh Loka, Daolang Huang, Ulpu Remes, Samuel Kaski, Luigi Acerbi
Amortized meta-learning methods based on pre-training have propelled fields like natural language processing and vision.
no code implementations • 15 Oct 2024 • Hossein Abdi, Mingfei Sun, Andi Zhang, Samuel Kaski, Wei Pan
Training large models with millions or even billions of parameters from scratch incurs substantial computational costs.
1 code implementation • 10 Oct 2024 • Ayush Bharti, Daolang Huang, Samuel Kaski, François-Xavier Briol
Simulation-based inference (SBI) is the preferred framework for estimating parameters of intractable models in science and engineering.
no code implementations • 10 Oct 2024 • Fabio S. Ferreira, John Ashburner, Arabella Bouzigues, Chatrin Suksasilp, Lucy L. Russell, Phoebe H. Foster, Eve Ferry-Bolder, John C. van Swieten, Lize C. Jiskoot, Harro Seelaar, Raquel Sanchez-Valle, Robert Laforce, Caroline Graff, Daniela Galimberti, Rik Vandenberghe, Alexandre de Mendonca, Pietro Tiraboschi, Isabel Santana, Alexander Gerhard, Johannes Levin, Sandro Sorbi, Markus Otto, Florence Pasquier, Simon Ducharme, Chris R. Butler, Isabelle Le Ber, Elizabeth Finger, Maria C. Tartaglia, Mario Masellis, James B. Rowe, Matthis Synofzik, Fermin Moreno, Barbara Borroni, Samuel Kaski, Jonathan D. Rohrer, Janaina Mourao-Miranda
These findings underscore the potential of sparse GFA for integrating multiple data modalities and identifying interpretable latent disease factors that can improve the characterization and stratification of patients with neurological and mental health disorders.
1 code implementation • 12 Aug 2024 • Rafał Karczewski, Samuel Kaski, Markus Heinonen, Vikas Garg
Several generative models with elaborate training and sampling procedures have been proposed recently to accelerate structure-based drug design (SBDD); however, perplexingly, their empirical performance turns out to be suboptimal.
no code implementations • 25 Jun 2024 • Stephen Menary, Samuel Kaski, Andre Freitas
Recent works have shown that transformers can solve contextual reasoning tasks by internally executing computational graphs called circuits.
1 code implementation • 24 Jun 2024 • Trung Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski
Deep neural networks (DNNs) excel on clean images but struggle with corrupted ones.
no code implementations • 5 Jun 2024 • Tiago da Silva, Luiz Max Carvalho, Amauri Souza, Samuel Kaski, Diego Mesquita
First, in parallel, we train a local GFlowNet targeting each $R_n$ and send the resulting models to the server.
1 code implementation • 30 May 2024 • Minttu Alakuijala, Reginald McLean, Isaac Woungang, Nariman Farsad, Samuel Kaski, Pekka Marttinen, Kai Yuan
Natural language is often the easiest and most convenient modality for humans to specify tasks for robots.
no code implementations • 26 May 2024 • Anjie Liu, Jianhong Wang, Haoxuan Li, Xu Chen, Jun Wang, Samuel Kaski, Mengyue Yang
In human-AI interaction, a prominent goal is to attain human`s desirable outcome with the assistance of AI agents, which can be ideally delineated as a problem of seeking the optimal Nash Equilibrium that matches the human`s desirable outcome.
no code implementations • 23 May 2024 • Marshal Arijona Sinaga, Julien Martinelli, Vikas Garg, Samuel Kaski
Such a model can be seamlessly integrated into the acquisition function, thus leading to candidate design pairs that elegantly trade informativeness and ease of comparison for the human expert.
no code implementations • 7 Mar 2024 • Ali Khoshvishkaie, Petrus Mikkola, Pierre-Alexandre Murena, Samuel Kaski
We introduce a cooperative Bayesian optimization problem for optimizing black-box functions of two variables where two agents choose together at which points to query the function but have only control over one variable each.
no code implementations • 7 Mar 2024 • Erik Nascimento, Diego Mesquita, Samuel Kaski, Amauri H Souza
While networks for tabular or image data are usually overconfident, recent works have shown that graph neural networks (GNNs) show the opposite behavior for node-level classification.
no code implementations • 5 Mar 2024 • Shibei Zhu, Tran Nguyen Le, Samuel Kaski, Ville Kyrki
We consider a type of collaboration in a shared-autonomy fashion, where both a human operator and an assistive robot act simultaneously in the same task space that affects each other's actions.
1 code implementation • 23 Feb 2024 • Jianhong Wang, Yang Li, Yuan Zhang, Wei Pan, Samuel Kaski
Ad hoc teamwork poses a challenging problem, requiring the design of an agent to collaborate with teammates without prior coordination or joint training.
1 code implementation • 6 Nov 2023 • Manuel Haussmann, Tran Minh Son Le, Viivi Halla-aho, Samu Kurki, Jussi V. Leinonen, Miika Koskinen, Samuel Kaski, Harri Lähdesmäki
Compared to previous methods, our results show improved performance both for direct treatment effect estimation as well as for effect estimation via patient matching.
no code implementations • 23 Oct 2023 • Sabina J. Sloman, Ayush Bharti, Julien Martinelli, Samuel Kaski
However, the introduction of nuisance parameters can lead to bias in the Bayesian learner's estimate of the target parameters, a phenomenon we refer to as negative interference.
2 code implementations • 19 Oct 2023 • Sophie Wharrie, Lisa Eick, Lotta Mäkinen, Andrea Ganna, Samuel Kaski, FinnGen
This was assessed for a variety of tasks that considered both new patients from the training population (UK Biobank) and a new population (FinnGen).
1 code implementation • 17 Oct 2023 • Quentin Bouniot, Ievgen Redko, Anton Mallasto, Charlotte Laclau, Karol Arndt, Oliver Struckmeier, Markus Heinonen, Ville Kyrki, Samuel Kaski
In the last decade, we have witnessed the introduction of several novel deep neural network (DNN) architectures exhibiting ever-increasing performance across diverse tasks.
1 code implementation • NeurIPS 2023 • Timur Garipov, Sebastiaan De Peuter, Ge Yang, Vikas Garg, Samuel Kaski, Tommi Jaakkola
A key challenge in composing iterative generative processes, such as GFlowNets and diffusion models, is that to realize the desired target distribution, all steps of the generative process need to be coordinated, and satisfy delicate balance conditions.
no code implementations • 21 Sep 2023 • Tiago da Silva, Eliezer Silva, António Góis, Dominik Heider, Samuel Kaski, Diego Mesquita, Adèle Ribeiro
Surprisingly, while CD is a human-centered affair, no works have focused on building methods that both 1) output uncertainty estimates that can be verified by experts and 2) interact with those experts to iteratively refine CD.
1 code implementation • 9 Aug 2023 • Lukas Prediger, Joonas Jälkö, Antti Honkela, Samuel Kaski
Consider a setting where multiple parties holding sensitive data aim to collaboratively learn population level statistics, but pooling the sensitive data sets is not possible.
1 code implementation • 5 Jun 2023 • Trung Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski
To sidestep these difficulties, we propose First-order Repulsive Deep Ensemble (FoRDE), an ensemble learning method based on ParVI, which performs repulsion in the space of first-order input gradients.
1 code implementation • NeurIPS 2023 • Daolang Huang, Ayush Bharti, Amauri Souza, Luigi Acerbi, Samuel Kaski
Simulation-based inference (SBI) methods such as approximate Bayesian computation (ABC), synthetic likelihood, and neural posterior estimation (NPE) rely on simulating statistics to infer parameters of intractable likelihood models.
no code implementations • 23 May 2023 • Julien Martinelli, Ayush Bharti, Armi Tiihonen, S. T. John, Louis Filstroff, Sabina J. Sloman, Patrick Rinke, Samuel Kaski
Contextual Bayesian Optimization (CBO) efficiently optimizes black-box functions with respect to design variables, while simultaneously integrating contextual information regarding the environment, such as experimental conditions.
1 code implementation • 19 May 2023 • Alexander Nikitin, Letizia Iannucci, Samuel Kaski
Temporally indexed data are essential in a wide range of fields and of interest to machine learning researchers.
1 code implementation • 3 Mar 2023 • Alexander Aushev, Aini Putkonen, Gregoire Clarte, Suyog Chandramouli, Luigi Acerbi, Samuel Kaski, Andrew Howes
In this paper, we propose BOSMOS: an approach to experimental design that can select between computational models without tractable likelihoods.
1 code implementation • 7 Feb 2023 • Robert Loftin, Mustafa Mert Çelikok, Herke van Hoof, Samuel Kaski, Frans A. Oliehoek
A natural solution concept in such settings is the Stackelberg equilibrium, in which the ``leader'' agent selects the strategy that maximizes its own payoff given that the ``follower'' agent will choose their best response to this strategy.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
1 code implementation • 27 Jan 2023 • Ayush Bharti, Masha Naslidnyk, Oscar Key, Samuel Kaski, François-Xavier Briol
Likelihood-free inference methods typically make use of a distance between simulated and real data.
1 code implementation • 29 Nov 2022 • Alex Hämäläinen, Mustafa Mert Çelikok, Samuel Kaski
Probabilistic user modeling is essential for building machine learning systems in the ubiquitous cases with humans in the loop.
no code implementations • 28 Oct 2022 • Joonas Jälkö, Lukas Prediger, Antti Honkela, Samuel Kaski
Using this as prior knowledge we establish a link between the gradients of the variational parameters, and propose an efficient while simple fix for the problem to obtain a less noisy gradient estimator, which we call $\textit{aligned}$ gradients.
1 code implementation • 25 Oct 2022 • Petrus Mikkola, Julien Martinelli, Louis Filstroff, Samuel Kaski
Over the past decade, many algorithms have been proposed to integrate cheaper, lower-fidelity approximations of the objective function into the optimization process, with the goal of converging towards the global optimum at a reduced cost.
no code implementations • 12 Oct 2022 • Yogesh Verma, Samuel Kaski, Markus Heinonen, Vikas Garg
Generating new molecules is fundamental to advancing critical applications such as drug discovery and material synthesis.
1 code implementation • 29 Sep 2022 • Amauri H. Souza, Diego Mesquita, Samuel Kaski, Vikas Garg
Specifically, novel constructions reveal the inadequacy of MP-TGNs and WA-TGNs, proving that neither category subsumes the other.
no code implementations • 18 Aug 2022 • Daolang Huang, Louis Filstroff, Petrus Mikkola, Runkai Zheng, Samuel Kaski
We design a multi-task learning architecture for this task, with the goal of jointly eliciting the expert knowledge and minimizing the objective function.
2 code implementations • 23 Jun 2022 • Alexander Nikitin, Samuel Kaski
We propose a human-in-the-loop PdM approach in which a machine learning system predicts future problems in sets of workstations (computers, laptops, and servers).
1 code implementation • 6 Jun 2022 • Trung Trinh, Markus Heinonen, Luigi Acerbi, Samuel Kaski
In this paper, we interpret these latent noise variables as implicit representations of simple and domain-agnostic data perturbations during training, producing BNNs that perform well under covariate shift due to input corruptions.
2 code implementations • 28 May 2022 • Ossi Räisä, Joonas Jälkö, Samuel Kaski, Antti Honkela
For example, confidence intervals become too narrow, which we demonstrate with a simple experiment.
no code implementations • 3 Apr 2022 • Mustafa Mert Çelikok, Frans A. Oliehoek, Samuel Kaski
Centaurs are half-human, half-AI decision-makers where the AI's goal is to complement the human.
1 code implementation • 22 Feb 2022 • Daniel Augusto de Souza, Diego Mesquita, Samuel Kaski, Luigi Acerbi
While efficient, this framework is very sensitive to the quality of subposterior sampling.
2 code implementations • 15 Feb 2022 • Sebastiaan De Peuter, Samuel Kaski
We consider the problem of creating assistants that can help agents solve new sequential decision problems, assuming the agent is not able to specify the reward function explicitly to the assistant.
1 code implementation • 31 Jan 2022 • Tianyu Cui, Yogesh Kumar, Pekka Marttinen, Samuel Kaski
Similarity metrics such as representational similarity analysis (RSA) and centered kernel alignment (CKA) have been used to compare layer-wise representations between neural networks.
1 code implementation • 28 Jan 2022 • Ayush Bharti, Louis Filstroff, Samuel Kaski
Approximate Bayesian computation (ABC) is a popular likelihood-free inference method for models with intractable likelihood functions.
no code implementations • 16 Nov 2021 • Alexander Nikitin, ST John, Arno Solin, Samuel Kaski
Gaussian processes (GPs) provide a principled and direct approach for inference and learning on graphs.
2 code implementations • NeurIPS Workshop Deep_Invers 2021 • Alexander Aushev, Thong Tran, Henri Pesonen, Andrew Howes, Samuel Kaski
Likelihood-free inference (LFI) has been successfully applied to state-space models, where the likelihood of observations is not available but synthetic observations generated by a black-box simulator can be used for inference instead.
no code implementations • 27 Oct 2021 • tejas kulkarni, Joonas Jälkö, Samuel Kaski, Antti Honkela
In recent years, local differential privacy (LDP) has emerged as a technique of choice for privacy-preserving data collection in several scenarios when the aggregator is not trustworthy.
no code implementations • NeurIPS 2021 • Zheyang Shen, Markus Heinonen, Samuel Kaski
Parallel to LD, Stein variational gradient descent (SVGD) similarly minimizes the KL, albeit endowed with a novel Stein-Wasserstein distance, by deterministically transporting a set of particle samples, thus de-randomizes the stochastic diffusion process.
no code implementations • 4 Oct 2021 • Antti Keurulainen, Isak Westerlund, Ariel Kwiatkowski, Samuel Kaski, Alexander Ilin
We suggest a method, where we synthetically produce populations of agents with different behavioural patterns together with ground truth data of their behaviour, and use this data for training a meta-learner.
no code implementations • 4 Oct 2021 • Antti Keurulainen, Isak Westerlund, Samuel Kaski, Alexander Ilin
On the other hand, offline data about the behavior of the assisted agent might be available, but is non-trivial to take advantage of by methods such as offline reinforcement learning.
1 code implementation • 18 Aug 2021 • Zhirong Yang, Yuwei Chen, Denis Sedov, Samuel Kaski, Jukka Corander
In this family, much better cluster visualizations often appear with a parameter value different from the one corresponding to SNE.
no code implementations • 22 Jul 2021 • Sebastiaan De Peuter, Antti Oulasvirta, Samuel Kaski
AI for supporting designers needs to be rethought.
1 code implementation • 21 Jun 2021 • Pashupati Hegde, Çağatay Yıldız, Harri Lähdesmäki, Samuel Kaski, Markus Heinonen
Recent machine learning advances have proposed black-box estimation of unknown continuous-time system dynamics directly from data.
no code implementations • 8 Jun 2021 • Louis Filstroff, Iiris Sundin, Petrus Mikkola, Aleksei Tiulpin, Juuso Kylmäoja, Samuel Kaski
Active learning is usually applied to acquire labels of informative data points in supervised learning, to maximize accuracy in a sample-efficient way.
no code implementations • 25 May 2021 • Anton Mallasto, Karol Arndt, Markus Heinonen, Samuel Kaski, Ville Kyrki
In this paper, we present affine transport -- a variant of optimal transport, which models the mapping between state transition distributions between the source and target domains with an affine transformation.
no code implementations • 31 Mar 2021 • Betül Güvenç Paltun, Samuel Kaski, Hiroshi Mamitsuka
More specifically, we sequentially integrate five different data sets, which have not all been combined in earlier bioinformatic methods for predicting drug responses.
1 code implementation • 22 Mar 2021 • Lukas Prediger, Niki Loppi, Samuel Kaski, Antti Honkela
We present d3p, a software package designed to help fielding runtime efficient widely-applicable Bayesian inference under differential privacy guarantees.
no code implementations • 23 Feb 2021 • Alexander Nikitin, Samuel Kaski
Human-in-the-loop machine learning is widely used in artificial intelligence (AI) to elicit labels for data points from experts or to provide feedback on how close the predicted results are to the target.
no code implementations • 2 Nov 2020 • Charles Gadd, Markus Heinonen, Harri Lähdesmäki, Samuel Kaski
In model-based reinforcement learning efficiency is improved by learning to simulate the world dynamics.
no code implementations • 1 Nov 2020 • tejas kulkarni, Joonas Jälkö, Antti Koskela, Samuel Kaski, Antti Honkela
Generalized linear models (GLMs) such as logistic regression are among the most widely used arms in data analyst's repertoire and often used on sensitive datasets.
1 code implementation • 26 Oct 2020 • Trung Trinh, Samuel Kaski, Markus Heinonen
We introduce implicit Bayesian neural networks, a simple and scalable approach for uncertainty representation in deep learning.
1 code implementation • NeurIPS 2020 • Diego Mesquita, Amauri H. Souza, Samuel Kaski
In this paper, we build upon representative GNNs and introduce variants that challenge the need for locality-preserving representations, either using randomization or clustering on the complement graph.
no code implementations • 19 Oct 2020 • Anton Mallasto, Markus Heinonen, Samuel Kaski
In machine learning and computer vision, optimal transport has had significant success in learning generative models and defining metric distances between structured and stochastic data objects, that can be cast as probability measures.
no code implementations • 19 Oct 2020 • Razane Tajeddine, Joonas Jälkö, Samuel Kaski, Antti Honkela
We modify a secure multiparty computation (MPC) framework to combine MPC with differential privacy (DP), in order to use differentially private MPC effectively to learn a probabilistic generative model under DP on such vertically partitioned data.
no code implementations • 14 Sep 2020 • Mustafa Mert Celikok, Pierre-Alexandre Murena, Samuel Kaski
In sequential machine teaching, a teacher's objective is to provide the optimal sequence of inputs to sequential learners in order to guide them towards the best model.
1 code implementation • 10 Jul 2020 • Mikko A. Heikkilä, Antti Koskela, Kana Shimizu, Samuel Kaski, Antti Honkela
In this paper we combine additively homomorphic secure summation protocols with differential privacy in the so-called cross-silo federated learning setting.
1 code implementation • 18 Jun 2020 • Alexander Aushev, Henri Pesonen, Markus Heinonen, Jukka Corander, Samuel Kaski
In recent years, surrogate models have been successfully used in likelihood-free inference to decrease the number of simulator evaluations.
1 code implementation • 4 May 2020 • Fabio Colella, Pedram Daee, Jussi Jokinen, Antti Oulasvirta, Samuel Kaski
To verify this hypothesis, that humans steer and are able to improve performance by steering, we designed a function optimization task where a human and an optimization algorithm collaborate to find the maximum of a 1-dimensional function.
1 code implementation • 23 Apr 2020 • Khaoula El Mekkaoui, Diego Mesquita, Paul Blomstedt, Samuel Kaski
We apply conducive gradients to distributed stochastic gradient Langevin dynamics (DSGLD) and call the resulting method federated stochastic gradient Langevin dynamics (FSGLD).
no code implementations • 6 Apr 2020 • Tom Vander Aa, Xiangju Qin, Paul Blomstedt, Roel Wuyts, Wilfried Verachtert, Samuel Kaski
We show that the combination of the two methods gives substantial improvements in the scalability of BMF on web-scale datasets, when the goal is to reduce the wall-clock time.
no code implementations • 27 Feb 2020 • Yuxin Sun, Benny Chain, Samuel Kaski, John Shawe-Taylor
In many high dimensional classification or regression problems set in a biological context, the complete identification of the set of informative features is often as important as predictive accuracy, since this can provide mechanistic insight and conceptual understanding.
no code implementations • 24 Feb 2020 • Tianyu Cui, Aki Havulinna, Pekka Marttinen, Samuel Kaski
Encoding domain knowledge into the prior over the high-dimensional weight space of a neural network is challenging but essential in applications with limited data and weak signals.
no code implementations • 21 Feb 2020 • Owen Thomas, Raquel Sá-Leão, Hermínia de Lencastre, Samuel Kaski, Jukka Corander, Henri Pesonen
To advance the possibilities for performing likelihood-free inference in higher dimensional parameter spaces, we introduce an extension of the popular Bayesian optimisation based approach to approximate discrepancy functions in a probabilistic manner which lends itself to an efficient exploration of the parameter space.
2 code implementations • ICML 2020 • Petrus Mikkola, Milica Todorović, Jari Järvi, Patrick Rinke, Samuel Kaski
This is demonstrated in a user experiment in which the user feedback comes in the form of optimal position and orientation of a molecule adsorbing to a surface.
2 code implementations • 10 Dec 2019 • Joonas Jälkö, Eemil Lagerspetz, Jari Haukka, Sasu Tarkoma, Antti Honkela, Samuel Kaski
Differential privacy allows quantifying privacy loss resulting from accessing sensitive personal data.
no code implementations • 1 Dec 2019 • Mustafa Mert Çelikok, Tomi Peltola, Pedram Daee, Samuel Kaski
Understanding each other is the key to success in collaboration.
1 code implementation • 1 Nov 2019 • Tomi Peltola, Jussi Jokinen, Samuel Kaski
The strengths of the probabilistic formulation, in addition to providing a bounded rational account of the learning of the heuristic, include natural extensibility with additional cognitively plausible constraints and prior information, and the possibility to embed the heuristic as a subpart of a larger probabilistic model.
1 code implementation • 21 Oct 2019 • Homayun Afrabandpey, Tomi Peltola, Juho Piironen, Aki Vehtari, Samuel Kaski
Through experiments on real-word data sets, using decision trees as interpretable models and Bayesian additive regression models as reference models, we show that for the same level of interpretability, our approach generates more accurate models than the alternative of restricting the prior.
1 code implementation • 25 Aug 2019 • Jonathan Strahl, Jaakko Peltonen, Hiroshi Mamitsuka, Samuel Kaski
The identification and removal of contested edges adds no computational complexity to state-of-the-art graph-regularized matrix factorization, remaining linear with respect to the number of non-zeros.
Ranked #1 on
Recommendation Systems
on YahooMusic
(using extra training data)
no code implementations • 31 Jul 2019 • Xiangju Qin, Paul Blomstedt, Samuel Kaski
Matrix completion aims to predict missing elements in a partially observed data matrix which in typical applications, such as collaborative filtering, is large and extremely sparsely observed.
no code implementations • 23 May 2019 • Zheyang Shen, Markus Heinonen, Samuel Kaski
We introduce the convolutional spectral kernel (CSK), a novel family of non-stationary, nonparametric covariance kernels for Gaussian process (GP) models, derived from the convolution between two imaginary radial basis functions.
1 code implementation • 10 Apr 2019 • Iiris Sundin, Peter Schulam, Eero Siivola, Aki Vehtari, Suchi Saria, Samuel Kaski
Machine learning can help personalized decision support by learning models to predict individual treatment effects (ITE).
no code implementations • 11 Mar 2019 • Diego Mesquita, Paul Blomstedt, Samuel Kaski
While MCMC methods have become a main work-horse for Bayesian inference, scaling them to large distributed datasets is still a challenge.
no code implementations • 26 Feb 2019 • Homayun Afrabandpey, Tomi Peltola, Samuel Kaski
Learning predictive models from small high-dimensional data sets is a key problem in high-dimensional statistics.
no code implementations • 29 Jan 2019 • Teppo Niinimäki, Mikko Heikkilä, Antti Honkela, Samuel Kaski
Differentially private learning with genomic data is challenging because it is more difficult to guarantee the privacy in high dimensions.
1 code implementation • 24 Jan 2019 • Tianyu Cui, Pekka Marttinen, Samuel Kaski
Estimating global pairwise interaction effects, i. e., the difference between the joint effect and the sum of marginal effects of two input features, with uncertainty properly quantified, is centrally important in science applications.
1 code implementation • 27 Nov 2018 • Sami Remes, Markus Heinonen, Samuel Kaski
Spectral mixture kernels have been proposed as general-purpose, flexible kernels for learning and discovering more complicated patterns in the data.
no code implementations • 29 Oct 2018 • Charlie Rogers-Smith, Henri Pesonen, Samuel Kaski
Approximate Bayesian computation (ABC) methods can be used to sample from posterior distributions when the likelihood function is unavailable or intractable, as is often the case in biological systems.
no code implementations • 10 Oct 2018 • Zheyang Shen, Markus Heinonen, Samuel Kaski
The expressive power of Gaussian processes depends heavily on the choice of kernel.
1 code implementation • 9 Oct 2018 • Pashupati Hegde, Markus Heinonen, Harri Lähdesmäki, Samuel Kaski
We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function.
1 code implementation • 6 Oct 2018 • Kenneth Blomqvist, Samuel Kaski, Markus Heinonen
We propose deep convolutional Gaussian processes, a deep Gaussian process architecture with convolutional structure.
1 code implementation • NeurIPS 2019 • Tomi Peltola, Mustafa Mert Çelikok, Pedram Daee, Samuel Kaski
We formulate this sequential teaching problem, which current techniques in machine teaching do not address, as a Markov decision process, with the dynamics nesting a model of the learner and the actions being the teacher's responses.
1 code implementation • 18 Apr 2018 • Markus Heinonen, Maria Osmala, Henrik Mannerström, Janne Wallenius, Samuel Kaski, Juho Rousu, Harri Lähdesmäki
Flux analysis methods commonly place unrealistic assumptions on fluxes due to the convenience of formulating the problem as a linear programming model, and most methods ignore the notable uncertainty in flux estimates.
1 code implementation • 13 Mar 2018 • Pashupati Hegde, Markus Heinonen, Samuel Kaski
We propose a novel model family of zero-inflated Gaussian processes (ZiGP) for such zero-inflated datasets, produced by sparse kernels through learning a latent probit Gaussian process that can zero out kernel rows and columns whenever the signal is absent.
1 code implementation • 13 Oct 2017 • Pedram Daee, Tomi Peltola, Aki Vehtari, Samuel Kaski
In human-in-the-loop machine learning, the user provides information beyond that in the training data.
2 code implementations • 2 Aug 2017 • Jarno Lintusaari, Henri Vuollekoski, Antti Kangasrääsiö, Kusti Skytén, Marko Järvenpää, Pekka Marttinen, Michael U. Gutmann, Aki Vehtari, Jukka Corander, Samuel Kaski
The stand-alone ELFI graph can be used with any of the available inference methods without modifications.
1 code implementation • NeurIPS 2017 • Sami Remes, Markus Heinonen, Samuel Kaski
We propose non-stationary spectral kernels for Gaussian process regression.
no code implementations • 16 May 2017 • Yao Lu, Zhirong Yang, Juho Kannala, Samuel Kaski
A key to the problem is learning a representation of relations.
no code implementations • 9 May 2017 • Iiris Sundin, Tomi Peltola, Muntasir Mamun Majumder, Pedram Daee, Marta Soare, Homayun Afrabandpey, Caroline Heckman, Samuel Kaski, Pekka Marttinen
Predicting the efficacy of a drug for a given individual, using high-dimensional genomic measurements, is at the core of precision medicine.
no code implementations • 28 Mar 2017 • Antti Kangasrääsiö, Samuel Kaski
Inverse reinforcement learning (IRL) aims to explain observed strategic behavior by fitting reinforcement learning models to behavioral data.
1 code implementation • NeurIPS 2017 • Mikko Heikkilä, Eemil Lagerspetz, Samuel Kaski, Kana Shimizu, Sasu Tarkoma, Antti Honkela
Many applications of machine learning, for example in health care, would benefit from methods that can guarantee privacy of data subjects.
no code implementations • 2 Mar 2017 • Xiangju Qin, Paul Blomstedt, Eemeli Leppäaho, Pekka Parviainen, Samuel Kaski
Bayesian matrix factorization (BMF) is a powerful tool for producing low-rank representations of matrices and for predicting missing values and providing confidence intervals.
1 code implementation • 27 Feb 2017 • Sami Remes, Markus Heinonen, Samuel Kaski
We introduce a novel kernel that models input-dependent couplings across multiple latent processes.
no code implementations • 21 Feb 2017 • Makoto Yamada, Song Liu, Samuel Kaski
We propose an inlier-based outlier detection method capable of both identifying the outliers and explaining why they are outliers, by identifying the outlier-specific features.
1 code implementation • 10 Dec 2016 • Pedram Daee, Tomi Peltola, Marta Soare, Samuel Kaski
Prediction in a small-sized sample with a large number of covariates, the "small n, large p" problem, is challenging.
no code implementations • 8 Dec 2016 • Homayun Afrabandpey, Tomi Peltola, Samuel Kaski
The key idea is to use an interactive multidimensional-scaling (MDS) type scatterplot display of the features to elicit the similarity relationships, and then use the elicited relationships in the prior distribution of prediction parameters.
no code implementations • 7 Dec 2016 • Luana Micallef, Iiris Sundin, Pekka Marttinen, Muhammad Ammad-Ud-Din, Tomi Peltola, Marta Soare, Giulio Jacucci, Samuel Kaski
The main component of our approach is a user model that models the domain expert's knowledge of the relevance of different features for a prediction task.
no code implementations • 2 Dec 2016 • Antti Kangasrääsiö, Kumaripaba Athukorala, Andrew Howes, Jukka Corander, Samuel Kaski, Antti Oulasvirta
An important problem for HCI researchers is to estimate the parameter values of a cognitive model from behavioral data.
1 code implementation • 30 Nov 2016 • Owen Thomas, Ritabrata Dutta, Jukka Corander, Samuel Kaski, Michael U. Gutmann
The popular synthetic likelihood approach infers the parameters by modelling summary statistics of the data by a Gaussian probability distribution.
no code implementations • 12 Jul 2016 • Manuel J. A. Eugster, Tuukka Ruotsalo, Michiel M. Spapé, Oswald Barral, Niklas Ravaja, Giulio Jacucci, Samuel Kaski
We introduce a brain-information interface used for recommending information by relevance inferred directly from brain signals.
no code implementations • 11 Jun 2016 • Muhammad Ammad-Ud-Din, Suleiman A. Khan, Disha Malani, Astrid Murumägi, Olli Kallioniemi, Tero Aittokallio, Samuel Kaski
We demonstrate that pathway-response associations can be learned by the proposed model for the well known EGFR and MEK inhibitors.
no code implementations • 7 Jun 2016 • Antti Honkela, Mrinal Das, Arttu Nieminen, Onur Dikmen, Samuel Kaski
Good personalised predictions are vitally important in precision medicine, but genomic information on which the predictions are based is also particularly sensitive, as it directly identifies the patients and hence cannot easily be anonymised.
no code implementations • 20 May 2016 • Marta Soare, Muhammad Ammad-Ud-Din, Samuel Kaski
We consider regression under the "extremely small $n$ large $p$" condition, where the number of samples $n$ is so small compared to the dimensionality $p$ that predictors cannot be estimated without prior knowledge.
no code implementations • 30 Mar 2016 • Ritabrata Dutta, Paul Blomstedt, Samuel Kaski
Hierarchical models are versatile tools for joint modeling of data sets arising from different, but related, sources.
no code implementations • 22 Mar 2016 • Makoto Yamada, Koh Takeuchi, Tomoharu Iwata, John Shawe-Taylor, Samuel Kaski
We introduce the localized Lasso, which is suited for learning models that are both interpretable and have a high predictive power in problems with high dimensionality $d$ and small sample size $n$.
2 code implementations • 8 Feb 2016 • Sahely Bhadra, Samuel Kaski, Juho Rousu
In this paper, we introduce the first method that (1) can complete kernel matrices with completely missing rows and columns as opposed to individual missing kernel values, (2) does not require any of the kernels to be complete a priori, and (3) can tackle non-linear kernels.
no code implementations • 29 Dec 2015 • Kerstin Bunte, Eemeli Leppäaho, Inka Saarinen, Samuel Kaski
Motivation: Modelling methods that find structure in data are necessary with the current large volumes of genomic data, and there have been various efforts to find subsets of genes exhibiting consistent patterns over subsets of treatments.
no code implementations • 24 Dec 2015 • Seppo Virtanen, Homayun Afrabandpey, Samuel Kaski
The factorization is a generative model in which the display is parameterized as a part of the factorization and the other factors explain away the aspects not expressible in a two-dimensional display.
no code implementations • 17 Dec 2015 • Sami Remes, Tommi Mononen, Samuel Kaski
We propose a novel classification model for weak signal data, building upon a recent model for Bayesian multi-view learning, Group Factor Analysis (GFA).
no code implementations • 31 Aug 2015 • Pekka Parviainen, Samuel Kaski
We show that for dependency structures between groups to be expressible exactly, the data have to satisfy the so-called groupwise faithfulness assumption.
1 code implementation • 18 Aug 2015 • Markus Heinonen, Henrik Mannerström, Juho Rousu, Samuel Kaski, Harri Lähdesmäki
We present a novel approach for fully non-stationary Gaussian process regression (GPR), where all three key parameters -- noise variance, signal variance and lengthscale -- can be simultaneously input-dependent.
1 code implementation • 4 Jul 2015 • Makoto Yamada, Wenzhao Lian, Amit Goyal, Jianhui Chen, Kishan Wimalawarne, Suleiman A. Khan, Samuel Kaski, Hiroshi Mamitsuka, Yi Chang
We propose the convex factorization machine (CFM), which is a convex variant of the widely used Factorization Machines (FMs).
no code implementations • 19 May 2015 • Paul Blomstedt, Ritabrata Dutta, Sohan Seth, Alvis Brazma, Samuel Kaski
For retrieval of gene expression experiments, we use a probabilistic model called product partition model, which induces a clustering of genes that show similar expression patterns across a number of samples.
no code implementations • 19 Feb 2015 • Michael U. Gutmann, Jukka Corander, Ritabrata Dutta, Samuel Kaski
This approach faces at least two major difficulties: The first difficulty is the choice of the discrepancy measure which is used to judge whether the simulated data resemble the observed data.
no code implementations • 15 Dec 2014 • Suleiman A. Khan, Eemeli Leppäaho, Samuel Kaski
We introduce Bayesian multi-tensor factorization, a model that is the first Bayesian formulation for joint factorization of multiple matrices and tensors.
no code implementations • 21 Nov 2014 • Arto Klami, Seppo Virtanen, Eemeli Leppäaho, Samuel Kaski
Factor analysis provides linear factors that describe relationships between individual variables of a data set.
no code implementations • 27 Oct 2014 • Jussi Gillberg, Pekka Marttinen, Matti Pirinen, Antti J. Kangas, Pasi Soininen, Mehreen Ali, Aki S. Havulinna, Marjo-Riitta Marjo-Riitta Järvelin, Mika Ala-Korpela, Samuel Kaski
In high-dimensional data, structured noise caused by observed and unobserved factors affecting multiple target variables simultaneously, imposes a serious challenge for modeling, by masking the often weak signal.
no code implementations • 2 Oct 2014 • Zakria Hussain, Arto Klami, Jussi Kujala, Alex P. Leung, Kitsuchart Pasupa, Peter Auer, Samuel Kaski, Jorma Laaksonen, John Shawe-Taylor
It then retrieves images with a specialized online learning algorithm that balances the tradeoff between exploring new images and exploiting the already inferred interests of the user.
no code implementations • 18 Jul 2014 • Michael U. Gutmann, Ritabrata Dutta, Samuel Kaski, Jukka Corander
Increasingly complex generative models are being used across disciplines as they allow for realistic characterization of data, but a common difficulty with them is the prohibitively large computational cost to evaluate the likelihood function and thus to perform likelihood-based statistical inference.
no code implementations • 1 Apr 2014 • Ali Faisal, Jaakko Peltonen, Elisabeth Georgii, Johan Rung, Samuel Kaski
A main challenge of data-driven sciences is how to make maximal use of the progressively expanding databases of experimental datasets in order to keep research cumulative.
no code implementations • 19 Feb 2014 • Sohan Seth, John Shawe-Taylor, Samuel Kaski
To incorporate this information in the retrieval task, we suggest employing a retrieval metric that utilizes probabilistic models learned from the measurements.
no code implementations • 30 Dec 2013 • Suleiman A. Khan, Seppo Virtanen, Olli P Kallioniemi, Krister Wennerberg, Antti Poso, Samuel Kaski
Results: In this paper, we present the first comprehensive multi-set analysis on how the chemical structure of drugs impacts on ge-nome-wide gene expression across several cancer cell lines (CMap database).
no code implementations • 16 Oct 2013 • Jussi Gillberg, Pekka Marttinen, Matti Pirinen, Antti J. Kangas, Pasi Soininen, Marjo-Riitta Järvelin, Mika Ala-Korpela, Samuel Kaski
To facilitate the prediction of the weak effects, we constrain our model structure by introducing a novel Bayesian approach of sharing information between the regression model and the noise model.
no code implementations • 8 Oct 2013 • Ritabrata Dutta, Sohan Seth, Samuel Kaski
We address the problem of retrieving relevant experiments given a query experiment, motivated by the public databases of datasets in molecular biology and other experimental sciences, and the need of scientists to relate to earlier work on the level of actual measurement data.
no code implementations • 6 Nov 2012 • Mehmet Gönen, Suleiman A. Khan, Samuel Kaski
Our algorithm obtains the lowest Hamming loss values on 10 out of 14 multilabel classification data sets compared to five state-of-the-art multilabel learning algorithms.
no code implementations • 22 Sep 2011 • Leo Lahti, Laura L. Elo, Tero Aittokallio, Samuel Kaski
Probe-level models have led to improved performance in microarray studies but the various sources of probe-level contamination are still poorly understood.