Mohit Kumar

AAAI Conference 2026 Conference Paper

Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent (Abstract Reprint)

• Mohit Kumar
• Alexander Valentinitsch
• Magdalena Fuchs
• Mathias Brucker
• Juliana Bowles
• Adnan Husakovic
• Ali Abbas
• Bernhard A. Moser

This paper develops a novel mathematical framework for collaborative learning by means of geometrically inspired kernel machines which includes statements on the bounds of generalisation and approximation errors, and sample complexity. For classification problems, this approach allows us to learn bounded geometric structures around given data points and hence solve the global model learning problem in an efficient way by exploiting convexity properties of the related optimisation problem in a Reproducing Kernel Hilbert Space (RKHS). In this way, we can reduce classification problems to determining the closest bounded geometric structure from a given data point. Further advantages that come with our solution is that our approach does not require clients to perform multiple epochs of local optimisation using stochastic gradient descent, nor require rounds of communication between client/server for optimising the global model. We highlight that numerous experiments have shown that the proposed method is a competitive alternative to the state-of-the-art.

JAIR Journal 2025 Journal Article

Geometrically Inspired Kernel Machines for Collaborative Learning Beyond Gradient Descent

• Mohit Kumar
• Alexander Valentinitsch
• Magdalena Fuchs
• Mathias Brucker
• Juliana Bowles
• Adnan Husakovic
• Ali Abbas
• Bernhard A. Moser

This paper develops a novel mathematical framework for collaborative learning by means of geometrically inspired kernel machines which includes statements on the bounds of generalisation and approximation errors, and sample complexity. For classification problems, this approach allows us to learn bounded geometric structures around given data points and hence solve the global model learning problem in an efficient way by exploiting convexity properties of the related optimisation problem in a Reproducing Kernel Hilbert Space (RKHS). In this way, we can reduce classification problems to determining the closest bounded geometric structure from a given data point. Further advantages that come with our solution is that our approach does not require clients to perform multiple epochs of local optimisation using stochastic gradient descent, nor require rounds of communication between client/server for optimising the global model. We highlight that numerous experiments have shown that the proposed method is a competitive alternative to the state-of-the-art.

JAIR Journal 2024 Journal Article

On Mitigating the Utility-Loss in Differentially Private Learning: A New Perspective by a Geometrically Inspired Kernel Approach

• Mohit Kumar
• Bernhard A. Moser
• Lukas Fischer

Privacy-utility tradeoff remains as one of the fundamental issues of differentially private machine learning. This paper introduces a geometrically inspired kernel-based approach to mitigate the accuracy-loss issue in classification. In this approach, a representation of the affine hull of given data points is learned in Reproducing Kernel Hilbert Spaces (RKHS). This leads to a novel distance measure that hides privacy-sensitive information about individual data points and improves the privacy-utility tradeoff via significantly reducing the risk of membership inference attacks. The effectiveness of the approach is demonstrated through experiments on MNIST dataset, Freiburg groceries dataset, and a real biomedical dataset. It is verified that the approach remains computationally practical. The application of the approach to federated learning is considered and it is observed that the accuracy-loss due to data being distributed is either marginal or not significantly high.

IJCAI Conference 2024 Conference Paper

On Mitigating the Utility-Loss in Differentially Private Learning: A New Perspective by a Geometrically Inspired Kernel Approach (Abstract Reprint)

• Mohit Kumar
• Bernhard A. Moser
• Lukas Fischer

Privacy-utility tradeoff remains as one of the fundamental issues of differentially private machine learning. This paper introduces a geometrically inspired kernel-based approach to mitigate the accuracy-loss issue in classification. In this approach, a representation of the affine hull of given data points is learned in Reproducing Kernel Hilbert Spaces (RKHS). This leads to a novel distance measure that hides privacy-sensitive information about individual data points and improves the privacy-utility tradeoff via significantly reducing the risk of membership inference attacks. The effectiveness of the approach is demonstrated through experiments on MNIST dataset, Freiburg groceries dataset, and a real biomedical dataset. It is verified that the approach remains computationally practical. The application of the approach to federated learning is considered and it is observed that the accuracy-loss due to data being distributed is either marginal or not significantly high.

EAAI Journal 2024 Journal Article

Variational Bayesian deep fuzzy models for interpretable classification

• Mohit Kumar
• Sukhvir Singh
• Juliana Bowles

AIJ Journal 2023 Journal Article

Learning MAX-SAT from contextual examples for combinatorial optimisation

• Mohit Kumar
• Samuel Kolb
• Stefano Teso
• Luc De Raedt

AAAI Conference 2021 System Paper

Democratizing Constraint Satisfaction Problems through Machine Learning

• Mohit Kumar
• Samuel Kolb
• Clement Gautrais
• Luc De Raedt

Constraint satisfaction problems (CSPs) are used widely, especially in the field of operations research, to model various real world problems like scheduling or planning. However, modelling a problem as a CSP is not trivial, it is labour intensive and requires both modelling and domain expertise. The emerging field of constraint learning deals with this problem by automatically learning constraints from a given dataset. While there are several interesting approaches for constraint learning, these works are hard to access for a non-expert user. Furthermore, different approaches have different underlying formalism and require different setups before they can be used. This demo paper combines these researches and brings it to non-expert users in the form of an interactive Excel plugin. To do this, we translate different formalism for specifying CSPs into a common language, which allows multiple constraint learners to coexist, making this plugin more powerful than individual constraint learners. Moreover, we integrate learning of CSPs from data with solving them, making it a self sufficient plugin. For the developers of different constraint learners, we provide an API that can be used to integrate their work with this plugin by implementing a handful of functions.

AAAI Conference 2020 Conference Paper

Learning MAX-SAT from Contextual Examples for Combinatorial Optimisation

• Mohit Kumar
• Samuel Kolb
• Stefano Teso
• Luc De Raedt

Combinatorial optimization problems are ubiquitous in artificial intelligence. Designing the underlying models, however, requires substantial expertise, which is a limiting factor in practice. The models typically consist of hard and soft constraints, or combine hard constraints with a preference function. We introduce a novel setting for learning combinatorial optimisation problems from contextual examples. These positive and negative examples show – in a particular context – whether the solutions are good enough or not. We develop our framework using the MAX-SAT formalism. We provide learnability results within the realizable and agnostic settings, as well as HASSLE, an implementation based on syntax-guided synthesis and showcase its promise on recovering synthetic and benchmark instances from examples.

IJCAI Conference 2019 Conference Paper

Acquiring Integer Programs from Data

• Mohit Kumar
• Stefano Teso
• Luc De Raedt

Integer programming (IP) is widely used within operations research to model and solve complex combinatorial problems such as personnel rostering and assignment problems. Modelling such problems is difficult for non-experts and expensive when hiring domain experts to perform the modelling. For many tasks, however, examples of working solutions are readily available. We propose ARNOLD, an approach that partially automates the modelling step by learning an integer program from example solutions. Contrary to existing alternatives, ARNOLD natively handles multi-dimensional quantities and non-linear operations, which are at the core of IP problems, and it only requires examples of feasible solution. The main challenge is to efficiently explore the space of possible programs. Our approach pairs a general-to-specific traversal strategy with a nested lexicographic ordering in order to prune large portions of the space of candidate constraints while avoiding visiting the same candidate multiple times. Our empirical evaluation shows that ARNOLD can acquire models for a number of realistic benchmark problems

AAAI Conference 2018 Conference Paper

Decomposition Strategies for Constructive Preference Elicitation

• Paolo Dragone
• Stefano Teso
• Mohit Kumar
• Andrea Passerini

We tackle the problem of constructive preference elicitation, that is the problem of learning user preferences over very large decision problems, involving a combinatorial space of possible outcomes. In this setting, the suggested configuration is synthesized on-the-fly by solving a constrained optimization problem, while the preferences are learned iteratively by interacting with the user. Previous work has shown that Coactive Learning is a suitable method for learning user preferences in constructive scenarios. In Coactive Learning the user provides feedback to the algorithm in the form of an improvement to a suggested configuration. When the problem involves many decision variables and constraints, this type of interaction poses a significant cognitive burden on the user. We propose a decomposition technique for large preferencebased decision problems relying exclusively on inference and feedback over partial configurations. This has the clear advantage of drastically reducing the user cognitive load. Additionally, part-wise inference can be (up to exponentially) less computationally demanding than inference over full configurations. We discuss the theoretical implications of working with parts and present promising empirical results on one synthetic and two realistic constructive problems.

IJCAI Conference 2007 Conference Paper

• Mohit Kumar
• Nikesh Garera
• Alexander I. Rudnicky

We describe a briefing system that learns to predict the contents of reports generated by users who create periodic (weekly) reports as part of their normal activity. The system observes content-selection choices that users make and builds a predictive model that could, for example, be used to generate an initial draft report. Using a feature of the interface the system also collects information about potential user-specific features. The system was evaluated under realistic conditions, by collecting data in a project-based university course where student group leaders were tasked with preparing weekly reports for the benefit of the instructors, using the material from individual student reports. This paper addresses the question of whether data derived from the implicit supervision provided by end-users is robust enough to support not only model parameter tuning but also a form of feature discovery. Results indicate that this is the case: system performance improves based on the feedback from user activity. We find that individual learned models (and features) are user-specific, although not completely idiosyncratic. This may suggest that approaches which seek to optimize models globally (say over a large corpus of data) may not in fact produce results acceptable to all individuals.