M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling

• URL: http://arxiv.org/abs/2403.13728v3
• Date: Tue, 11 Mar 2025 14:02:30 GMT
• Title: M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling
• Authors: Xudong Sun, Nutan Chen, Alexej Gossmann, Matteo Wohlrapp, Yu Xing, Carla Feistner, Emilio Dorigatt, Felix Drost, Daniele Scarcella, Lisa Beer, Carsten Marr,
• Abstract summary: A probabilistic graphical model is proposed, modeling the joint model parameter and multiplier evolution.<n>We address multi-objective model parameter optimization via a surrogate single objective penalty loss.
• Score: 4.369346338392536
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A probabilistic graphical model is proposed, modeling the joint model parameter and multiplier evolution, with a hypervolume based likelihood, promoting multi-objective descent in structural risk minimization. We address multi-objective model parameter optimization via a surrogate single objective penalty loss with time-varying multipliers, equivalent to online scheduling of loss landscape. The multi-objective descent goal is dispatched hierarchically into a series of constraint optimization sub-problems with shrinking bounds according to Pareto dominance. The bound serves as setpoint for the low-level multiplier controller to schedule loss landscapes via output feedback of each loss term. Our method forms closed loop of model parameter dynamic, circumvents excessive memory requirements and extra computational burden of existing multi-objective deep learning methods, and is robust against controller hyperparameter variation, demonstrated on domain generalization tasks with multi-dimensional regularization losses.

Related papers

• You Only Train Once [11.97836331714694]
  You Only Train Once (YOTO) contributes to limiting training to one shot for the latter aspect of losses selection and weighting.<n>We leverage the differentiability of the composite loss formulation which is widely used for optimizing multiple empirical losses simultaneously.<n>We show that YOTO consistently outperforms the best grid-search model on unseen test data.
  arXiv  Detail & Related papers  (2025-06-04T18:04:58Z)
• Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning [59.6658995479243]
  We propose texttext-Perturb-and-Merge (P&M), a novel continual learning framework that integrates model merging into the CL paradigm to avoid forgetting.<n>Through theoretical analysis, we minimize the total loss increase across all tasks and derive an analytical solution for the optimal merging coefficient.<n>Our proposed approach achieves state-of-the-art performance on several continual learning benchmark datasets.
  arXiv  Detail & Related papers  (2025-05-28T14:14:19Z)
• The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks [56.37880529653111]
  The demand for large computation model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications.<n>In this paper, we investigate the LAIM-inference scheme, where a pre-trained LAIM is pruned and partitioned into on-device and on-server sub-models for deployment.
  arXiv  Detail & Related papers  (2025-05-14T08:18:55Z)
• VRVVC: Variable-Rate NeRF-Based Volumetric Video Compression [59.14355576912495]
  NeRF-based video has revolutionized visual media by delivering photorealistic Free-Viewpoint Video (FVV) experiences. The substantial data volumes pose significant challenges for storage and transmission. We propose VRVVC, a novel end-to-end joint variable-rate framework for video compression.
  arXiv  Detail & Related papers  (2024-12-16T01:28:04Z)
• Q-VLM: Post-training Quantization for Large Vision-Language Models [73.19871905102545]
  We propose a post-training quantization framework of large vision-language models (LVLMs) for efficient multi-modal inference. We mine the cross-layer dependency that significantly influences discretization errors of the entire vision-language model, and embed this dependency into optimal quantization strategy. Experimental results demonstrate that our method compresses the memory by 2.78x and increase generate speed by 1.44x about 13B LLaVA model without performance degradation.
  arXiv  Detail & Related papers  (2024-10-10T17:02:48Z)
• LoRTA: Low Rank Tensor Adaptation of Large Language Models [70.32218116940393]
  Low Rank Adaptation (LoRA) is a popular Efficient Fine Tuning (PEFT) method. We propose a higher-order Candecomp/Parafac (CP) decomposition, enabling a more compact and flexible representation. Our method can achieve a reduction in the number of parameters while maintaining comparable performance.
  arXiv  Detail & Related papers  (2024-10-05T06:59:50Z)
• Real-time optimal control of high-dimensional parametrized systems by deep learning-based reduced order models [3.5161229331588095]
  We propose a non-intrusive Deep Learning-based Reduced Order Modeling (DL-ROM) technique for the rapid control of systems described in terms of parametrized PDEs in multiple scenarios. After (i) data generation, (ii) dimensionality reduction, and (iii) neural networks training in the offline phase, optimal control strategies can be rapidly retrieved in an online phase for any scenario of interest.
  arXiv  Detail & Related papers  (2024-09-09T15:20:24Z)
• A Re-solving Heuristic for Dynamic Assortment Optimization with Knapsack Constraints [14.990988698038686]
  We consider a multi-stage dynamic assortment optimization problem with multi-nomial choice modeling (MNL) under resource knapsack constraints. With the exact optimal dynamic assortment solution being computationally intractable, a practical strategy is to adopt the re-solving technique that periodically re-optimizes deterministic linear programs. We propose a new epoch-based re-solving algorithm that effectively transforms the denominator of the objective into the constraint.
  arXiv  Detail & Related papers  (2024-07-08T02:40:20Z)
• Trajectory-Based Multi-Objective Hyperparameter Optimization for Model Retraining [8.598456741786801]
  We present a novel trajectory-based multi-objective Bayesian optimization algorithm. Our algorithm outperforms the state-of-the-art multi-objectives in both locating better trade-offs and tuning efficiency.
  arXiv  Detail & Related papers  (2024-05-24T07:43:45Z)
• Transformer-based Stagewise Decomposition for Large-Scale Multistage Stochastic Optimization [1.3124513975412255]
  We introduce TranSDDP, a novel Transformer-based stagewise decomposition algorithm. We show it efficiently generates a piecewise linear approximation for the value function.
  arXiv  Detail & Related papers  (2024-04-03T09:08:15Z)
• Diffusion Model-Based Multiobjective Optimization for Gasoline Blending Scheduling [30.040728803996256]
  Gasoline blending scheduling uses resource allocation and operation sequencing to meet a refinery's production requirements. The presence of nonlinearity, integer constraints, and a large number of decision variables adds complexity to this problem. This paper introduces a novel multiobjective optimization approach driven by a diffusion model (named DMO)
  arXiv  Detail & Related papers  (2024-02-04T05:46:28Z)
• Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model [81.55141188169621]
  We equip PEFT with a cross-block orchestration mechanism to enable the adaptation of the Segment Anything Model (SAM) to various downstream scenarios. We propose an intra-block enhancement module, which introduces a linear projection head whose weights are generated from a hyper-complex layer. Our proposed approach consistently improves the segmentation performance significantly on novel scenarios with only around 1K additional parameters.
  arXiv  Detail & Related papers  (2023-11-28T11:23:34Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• Multi-fidelity reduced-order surrogate modeling [5.346062841242067]
  We present a new data-driven strategy that combines dimensionality reduction with multi-fidelity neural network surrogates. We show that the onset of instabilities and transients are well captured by this surrogate technique.
  arXiv  Detail & Related papers  (2023-09-01T08:16:53Z)
• An iterative multi-fidelity approach for model order reduction of multi-dimensional input parametric PDE systems [0.0]
  We propose a sampling parametric strategy for the reduction of large-scale PDE systems with multidimensional input parametric spaces. It is achieved by exploiting low-fidelity models throughout the parametric space to sample points using an efficient sampling strategy. Since the proposed methodology leverages the use of low-fidelity models to assimilate the solution database, it significantly reduces the computational cost in the offline stage.
  arXiv  Detail & Related papers  (2023-01-23T15:25:58Z)
• Multi-Objective Policy Gradients with Topological Constraints [108.10241442630289]
  We present a new algorithm for a policy gradient in TMDPs by a simple extension of the proximal policy optimization (PPO) algorithm. We demonstrate this on a real-world multiple-objective navigation problem with an arbitrary ordering of objectives both in simulation and on a real robot.
  arXiv  Detail & Related papers  (2022-09-15T07:22:58Z)
• Robust Constrained Multi-objective Evolutionary Algorithm based on Polynomial Chaos Expansion for Trajectory Optimization [0.0]
  The proposed method rewrites a robust formulation into a deterministic problem via the PCE. As a case study, the landing trajectory design of supersonic transport (SST) with wind uncertainty is optimized.
  arXiv  Detail & Related papers  (2022-05-23T15:33:05Z)
• Multi-Agent Deep Reinforcement Learning in Vehicular OCC [14.685237010856953]
  We introduce a spectral efficiency optimization approach in vehicular OCC. We model the optimization problem as a Markov decision process (MDP) to enable the use of solutions that can be applied online. We verify the performance of our proposed scheme through extensive simulations and compare it with various variants of our approach and a random method.
  arXiv  Detail & Related papers  (2022-05-05T14:25:54Z)
• Neural Stochastic Dual Dynamic Programming [99.80617899593526]
  We introduce a trainable neural model that learns to map problem instances to a piece-wise linear value function. $nu$-SDDP can significantly reduce problem solving cost without sacrificing solution quality.
  arXiv  Detail & Related papers  (2021-12-01T22:55:23Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)
• Adaptive pruning-based optimization of parameterized quantum circuits [62.997667081978825]
  Variisy hybrid quantum-classical algorithms are powerful tools to maximize the use of Noisy Intermediate Scale Quantum devices. We propose a strategy for such ansatze used in variational quantum algorithms, which we call "Efficient Circuit Training" (PECT) Instead of optimizing all of the ansatz parameters at once, PECT launches a sequence of variational algorithms.
  arXiv  Detail & Related papers  (2020-10-01T18:14:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.