This paper surveys gradient-based multi-objective deep learning methods.
problem Balancing multiple conflicting objectives in deep learning models.
method Gradient-based techniques adapted from Multi-Objective Optimization.
result Comprehensive survey of gradient-based multi-objective deep learning algorithms.
Deep learning agent improves pedestrian navigation in urban environments.
problem Autonomous driving among pedestrians in urban areas.
method Multi-objective deep reinforcement learning using a deep Q-learning variant.
result The multi-objective DQN agent outperforms single-objective DQN in various environments.
The paper explores a Multi-Objective RL approach for trading that generalizes reward functions.
problem Improving performance in single-asset trading through adaptive reward functions.
method Developed a Multi-Objective Deep Reinforcement Learning algorithm to generalize reward functions and discount factors.
result The Multi-Objective algorithm demonstrates increased predictive stability and better performance in sparse reward scenarios.
This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We develop a high-performance MODRL framework that supports both single-policy and multi-policy strategies, as well as both linear and non-linear approaches to action selection. The experimental …
Proposes baselines for joint NAS and HPO optimization.
problem Joint optimization of neural architecture and hyperparameters for multiple objectives.
method Extends existing methods to jointly optimize with multiple objectives.
result Serves as simple baselines for future multi-objective joint NAS + HPO research.
MERLIN tackles multi-objective task scheduling with hierarchical DRL, outperforming existing methods.
problem Optimizing multiple conflicting constraints in multi-objective task scheduling with varying queue sizes.
method Hierarchical deep reinforcement learning approach to manage large queues efficiently.
result MERLIN outperforms existing methods by a large margin (>22%) on multiple queue sizes.
this paper has been withdrawn
Many real-world decision problems are characterized by multiple conflicting objectives which must be balanced based on their relative importance. In the dynamic weights setting the relative importance changes over time and specialized algorithms that deal with such change, such as a tabular Reinforcement Learning (RL) …
In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. Multi-task learning is inherently a multi-objective problem because different tasks may conflict, necessitating a trade-off. A common compromise is to optimize a proxy objective that minimizes a weighted linear combination o…
New algorithm improves fairness and robustness in federated learning.
problem Ensuring fairness and robustness in federated learning.
method Formulated federated learning as multi-objective optimization and proposed FedMGDA+.
result FedMGDA+ converges to Pareto stationary solutions, improving performance.
Proof of convergence for multi-objective optimization using inverse reinforcement learning.
problem Proving convergence in multi-objective optimization problems.
method Wasserstein inverse reinforcement learning with projective subgradient method and gradient descent.
result Convergence of inverse reinforcement learning for multi-objective optimization.
Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue that this is an unnecessary limitation and instead, the reward function should be provided to the learn…
Proof shows imitation of expert's reward and solutions in multi-objective optimization.
problem Multi-objective optimization with reward and solution imitation.
method Wasserstein inverse reinforcement learning.
result Wasserstein inverse reinforcement learning enables imitation of expert's reward and solutions in multi-objective optimization.
Develops a new method to improve performance in multi-objective learning problems.
problem Gradient bias in multi-objective learning leading to degraded performance.
method Stochastic Multi-objective gradient Correction (MoCo) method that guarantees convergence without increasing batch size.
result Demonstrates effectiveness of MoCo method in simulations on multi-task learning.
MO-PaDGAN improves multi-objective optimization by generating diverse and high-performing designs.
problem Challenges in parameterizing engineering designs for multi-objective optimization.
method MO-PaDGAN uses a generative adversarial network with a Determinantal Point Processes loss function to address these challenges.
result MO-PaDGAN generates designs with improved performance and coverage, even surpassing training data.
PiVoT improves real-time multi-object detection and tracking in clutter.
problem Challenges in multi-object detection and tracking from noisy point clouds.
method Variational inference for fast, clutter-resilient multi-object tracking.
result Substantial performance improvement over existing Bayesian trackers.
Unified framework for multi-objective curriculum learning in robotics.
problem Improving sample efficiency and final performance in robotic policy learning.
method Unified automatic curriculum learning framework with multi-task hyper-net and flexible memory mechanism.
result Superior performance compared to state-of-the-art methods in robotic manipulation tasks.
This work fills the gap in understanding multi-objective learning generalization.
problem Lack of statistical learning theory insights into multi-objective learning generalization.
method Established generalization bounds and excess bounds for multi-objective learning.
result Showed that all Pareto-optimal solutions can be approximated by empirically Pareto-optimal ones, but not vice versa.
Paper proposes a new method for designing materials using deep learning.
problem Designing high-performance material distributions from given distributions.
method Iterative process of selecting, generating, and merging material distributions using a deep generative model.
result The method improves material performance through iterative refinement.
A new method for optimizing hierarchical multi-objective problems.
problem Symmetry and neglect of objective hierarchy in existing multi-objective methods.
method Priority-Constrained Descent (PCD) framework exploiting hierarchical objective structures.
result Pareto dominance and better per-objective performance with secondary progress guarantees.
Proposes a fairness criterion for multi-objective optimization in classification.
problem Ensuring fairness in classification models across different groups.
method Formulates a minimax Pareto fairness criterion and provides an optimization algorithm.
result Demonstrates improved fairness compared to existing methods on various real-world datasets.
This paper introduces multi-objective hyperparameter optimization in machine learning.
problem Optimizing machine learning pipelines for multiple objectives, not just accuracy.
method Survey of optimization strategies and applications in multi-objective hyperparameter optimization.
result The importance and utility of multi-objective hyperparameter optimization in applied machine learning.
The design of machine learning systems often requires trading off different objectives, for example, prediction error and energy consumption for deep neural networks (DNNs). Typically, no single design performs well in all objectives; therefore, finding Pareto-optimal designs is of interest. The search for Pareto-optim…
A new method for diverse Pareto solutions in multi-objective learning.
problem Maximizing diversity while maximizing hypervolume in Pareto solutions.
method Annealed Stein Variational Gradient Descent (SVGD) with diverse gradient directions.
result SVH-MOL achieves superior performance in multi-objective and multi-task learning.
Enhanced tabular benchmarks for energy-efficient neural architecture search.
problem Energy consumption in deep learning models.
method Introducing EC-NAS, an enhanced tabular benchmark with energy consumption data.
result EC-NAS reveals a balance between energy usage and accuracy in neural architecture search.
Develops NPSVC++ to improve NPSVC performance through representation learning.
problem Feature suboptimality and class dependency in NPSVC training.
method Multi-objective optimization and end-to-end learning of NPSVC and its features.
result NPSVC++ ensures feature optimality across classes, overcoming training issues.
Proposes new stochastic algorithms for multi-objective optimization.
problem Multi-objective optimization in machine learning problems.
method Direction-oriented multi-objective formulation and Stochastic Direction-oriented Multi-objective Gradient descent (SDMGrad).
result Stochastic algorithms converge to Pareto stationary points with improved complexities.
FanG-HPO optimizes machine learning models for fairness and low energy consumption.
problem Bias in machine learning models and high energy consumption in hyperparameter optimization.
method Combines multi-objective and multiple information source Bayesian optimization.
result FanG-HPO identifies fair and energy-efficient machine learning models.
Paper tackles multi-object reinforcement learning, improving skill extrapolation.
problem Learning robust manipulation tasks in multi-object settings.
method Introduces a linear relation network module to enhance skill generalization.
result Agents can extrapolate and generalize to any new object number, scaling linearly.
This paper develops a method to approximate the whole Pareto set for expensive multi-objective optimization.
problem Finding an approximate Pareto front with limited expensive evaluations.
method A novel learning-based method to approximate the whole Pareto set for multi-objective Bayesian optimization (MOBO).
result The method approximates the whole Pareto set, not just a finite set, for MOBO.
New research shows Multi-Task Learning does not behave like Multi-Objective Optimization.
problem Applying MOO methods to MTL problems is not equivalent.
method Comparing MTL and MOO approaches on Multi-Fashion-MNIST datasets.
result A single model can perform as well as optimizing multiple objectives.
Proposes a novel algorithm for multi-objective reinforcement learning.
problem Challenges in setting numerical preferences for objectives in different units and scales.
method Learn action distributions for each objective and use supervised learning to fit a parametric policy.
result Demonstrates effectiveness on robotics tasks, allowing tracing out the space of nondominated solutions.
The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem have benefited from the representational power of deep models. This paper provid…
Reducing barriers to entry in large-scale ML markets, study shows multi-objective learning can lower data requirements.
problem Barriers to entry in emerging markets for large-scale machine learning models.
method Defined a multi-objective high-dimensional regression framework to study reputational damage and data requirements.
result The number of data points needed for a new company to enter the market can be significantly smaller than the incumbent company's dataset size.
Parallel BO method for multi-objective optimization with constraints.
problem Optimizing multiple objectives under constraints with expensive evaluations.
method PPESMOC, a batch method for simultaneous optimization of black-box functions.
result Empirical evidence shows PPESMOC is effective for multi-objective optimization with constraints.
Deep generative models (DGMs) have shown promise in image generation. However, most of the existing work learn the model by simply optimizing a divergence between the marginal distributions of the model and the data, and often fail to capture the rich structures and relations in multi-object images. Human knowledge is …
Bayesian nonparametrics adapt model complexity to diverse datasets.
problem Complex challenges across statistics, computer science, and engineering.
method Flexible Bayesian nonparametric models that adapt model complexity.
result Bayesian nonparametrics offer innovative solutions to multi-object tracking.
Proposes MOGFNs for generating diverse Pareto optimal solutions in multi-objective optimization.
problem Generating diverse candidates in multi-objective optimization with conflicting objectives.
method Introduces MOGFNs based on GFlowNets, with two variants: MOGFN-PC and MOGFN-AL.
result Improved candidate diversity compared to existing methods.
CardiacGen generates realistic ECG signals for training deep learning models.
problem Creating realistic synthetic ECG signals for training deep learning models.
method Hierarchical deep generative model with multi-objective loss functions.
result Synthetic ECG signals from CardiacGen can be used for data augmentation and improve classifier performance.
Boosting theory extended to handle cost-sensitive and multi-objective losses.
problem Real-world prediction problems with different error costs.
method Developed a comprehensive theory of cost-sensitive and multi-objective boosting.
result Established a dichotomy for binary classification and a more intricate landscape for multiclass settings.
Algorithm identifies Pareto front in multi-objective bandits efficiently.
problem Sequentially learning the Pareto front in multi-objective bandits.
method Efficient algorithm achieving optimal sample complexity.
result Correct answer with high probability in minimal rounds.
The paper presents a method for generating well-calibrated prediction intervals using quality-driven deep ensembles.
problem Generating reliable prediction intervals for regression analysis.
method A multi-objective loss function combining quality measures for prediction intervals and point estimates, with a penalty function to ensure semantic integrity and stability.
result The method produces well-calibrated prediction intervals and point estimates, capturing both aleatoric and epistemic uncertainty.
MWGraD solves multi-objective distributional optimization using particle-based gradient descent.
problem Simultaneously minimize multiple objective functionals over probability distributions.
method Iterative particle-based algorithm MWGraD, estimating and aggregating Wasserstein gradients.
result Demonstrates effectiveness on synthetic and real-world datasets.
Federated learning is an emerging technique used to prevent the leakage of private information. Unlike centralized learning that needs to collect data from users and store them collectively on a cloud server, federated learning makes it possible to learn a global model while the data are distributed on the users' devic…
Bayesian optimisation framework for multi-objective decision-making from choice data.
problem Optimizing multi-objective functions via choice judgements.
method Gaussian process prior and novel likelihood model for choice data.
result Proposes a novel Bayesian framework for learning latent functions from choice data.
Improves multi-objective learning by adapting to local subintervals.
problem Learning a predictor satisfying multiple objectives in an online, changing data setting.
method Adapting an existing multi-objective learning method with an adaptive online algorithm.
result Improves predictions over subgroups and remains robust under distribution shift.
We present a framework, which we call Molecule Deep Q-Networks (MolDQN), for molecule optimization by combining domain knowledge of chemistry and state-of-the-art reinforcement learning techniques (double Q-learning and randomized value functions). We directly define modifications on molecules, thereby ensuring 100…
A new Adamize method improves multi-objective recommender systems.
problem Improving recommendation systems with multiple conflicting objectives.
method Developed a multi-objective model-agnostic Adamize method that corrects and stabilizes gradients.
result Significant improvements in recommendation systems, measured by hypervolume, coverage, and spacing.