arXiv subjects

Kazushi Kawamura

Publications and source records attributed to Kazushi Kawamura.

6 recordsLinked to original sources

arXiv2026

Annealed Mean Field Descent Is Highly Effective for Quadratic Unconstrained Binary Optimization

In recent years, formulating various combinatorial optimization problems as Quadratic Unconstrained Binary Optimization (QUBO) has gained significant attention as a promising approach for efficiently obtaining optimal or near-optimal solutions. While QUBO offers a general-purpose framework, existing solvers often struggle with performance variability across different problems. This paper (i) theoretically analyzes Mean Field Annealing (MFA) and its variants--which are representative QUBO solvers, and reveals that their underlying self-consistent equations do not necessarily represent the minimum condition of the Kullback-Leibler divergence between the mean-field approximated distribution and the exact distribution, and (ii) proposes a novel method, the Annealed Mean Field Descent (AMFD), which is designed to address this limitation by directly minimizing the divergence. Through extensive experiments on five benchmark combinatorial optimization problems (Maximum Cut Problem, Maximum Independent Set Problem, Traveling Salesman Problem, Quadratic Assignment Problem, and Graph Coloring Problem), we demonstrate that AMFD exhibits superior performance in many cases and reduced problem dependence compared to state-of-the-art QUBO solvers and Gurobi--a state-of-the-art versatile mathematical optimization solver not limited to QUBO.

math.OC↗

arXiv2025

Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression

This paper proposes a novel matrix quantization method, Binary Quadratic Quantization (BQQ). In contrast to conventional first-order quantization approaches, such as uniform quantization and binary coding quantization, that approximate real-valued matrices via linear combinations of binary bases, BQQ leverages the expressive power of binary quadratic expressions while maintaining an extremely compact data format. We validate our approach with two experiments: a matrix compression benchmark and post-training quantization (PTQ) on pretrained Vision Transformer-based models. Experimental results demonstrate that BQQ consistently achieves a superior trade-off between memory efficiency and reconstruction error than conventional methods for compressing diverse matrix data. It also delivers strong PTQ performance, even though we neither target state-of-the-art PTQ accuracy under tight memory constraints nor rely on PTQ-specific binary matrix optimization. For example, our proposed method outperforms the state-of-the-art PTQ method by up to 2.2\% and 59.1% on the ImageNet dataset under the calibration-based and data-free scenarios, respectively, with quantization equivalent to 2 bits. These findings highlight the surprising effectiveness of binary quadratic expressions for efficient matrix approximation and neural network compression.

cs.CV↗

arXiv2025

Partially Frozen Random Networks Contain Compact Strong Lottery Tickets

Randomly initialized dense networks contain subnetworks that achieve high accuracy without weight learning--strong lottery tickets (SLTs). Recently, Gadhikar et al. (2023) demonstrated that SLTs could also be found within a randomly pruned source network. This phenomenon can be exploited to further compress the small memory size required by SLTs. However, their method is limited to SLTs that are even sparser than the source, leading to worse accuracy due to unintentionally high sparsity. This paper proposes a method for reducing the SLT memory size without restricting the sparsity of the SLTs that can be found. A random subset of the initial weights is frozen by either permanently pruning them or locking them as a fixed part of the SLT, resulting in a smaller model size. Experimental results show that Edge-Popup (Ramanujan et al., 2020; Sreenivasan et al., 2022) finds SLTs with better accuracy-to-model size trade-off within frozen networks than within dense or randomly pruned source networks. In particular, freezing $70\%$ of a ResNet on ImageNet provides $3.3 \times$ compression compared to the SLT found within a dense counterpart, raises accuracy by up to $14.12$ points compared to the SLT found within a randomly pruned counterpart, and offers a better accuracy-model size trade-off than both.

cs.LG↗

arXiv2023

Multicoated and Folded Graph Neural Networks with Strong Lottery Tickets

The Strong Lottery Ticket Hypothesis (SLTH) demonstrates the existence of high-performing subnetworks within a randomly initialized model, discoverable through pruning a convolutional neural network (CNN) without any weight training. A recent study, called Untrained GNNs Tickets (UGT), expanded SLTH from CNNs to shallow graph neural networks (GNNs). However, discrepancies persist when comparing baseline models with learned dense weights. Additionally, there remains an unexplored area in applying SLTH to deeper GNNs, which, despite delivering improved accuracy with additional layers, suffer from excessive memory requirements. To address these challenges, this work utilizes Multicoated Supermasks (M-Sup), a scalar pruning mask method, and implements it in GNNs by proposing a strategy for setting its pruning thresholds adaptively. In the context of deep GNNs, this research uncovers the existence of untrained recurrent networks, which exhibit performance on par with their trained feed-forward counterparts. This paper also introduces the Multi-Stage Folding and Unshared Masks methods to expand the search space in terms of both architecture and parameters. Through the evaluation of various datasets, including the Open Graph Benchmark (OGB), this work establishes a triple-win scenario for SLTH-based GNNs: by achieving high sparsity, competitive performance, and high memory efficiency with up to 98.7\% reduction, it demonstrates suitability for energy-efficient graph processing.

cs.LG↗

arXiv2023

Mixing time and simulated annealing for the stochastic cellular automata

Finding a ground state of a given Hamiltonian of an Ising model on a graph $G=(V,E)$ is an important but hard problem. The standard approach for this kind of problem is the application of algorithms that rely on single-spin-flip Markov chain Monte Carlo methods, such as the simulated annealing based on Glauber or Metropolis dynamics. In this paper, we investigate a particular kind of stochastic cellular automata, in which all spins are updated independently and simultaneously. We prove that (i) if the temperature is fixed sufficiently high, then the mixing time is at most of order $\log|V|$, and that (ii) if the temperature drops in time $n$ as $1/\log n$, then the limiting measure is uniformly distributed over the ground states. We also provide some simulations of the algorithms studied in this paper implemented on a GPU and show their superior performance compared to the conventional simulated annealing.

math.PR↗

arXiv2022

Stochastic optimization: Glauber dynamics versus stochastic cellular automata

The topic we address in this paper concerns the minimization of a Hamiltonian function for an Ising model through the application of simulated annealing algorithms based on (single-site) Glauber dynamics and stochastic cellular automata (SCA). Some rigorous results are presented in order to justify the application of simulated annealing for a particular kind of SCA. After that, we compare the SCA algorithm and its variation, namely the $\varepsilon$-SCA algorithm, studied in this paper with the Glauber dynamics by analyzing their accuracy in obtaining optimal solutions for the max-cut problem on Erdős-Rényi random graphs, the traveling salesman problem (TSP), and the minimization of Gaussian and Bernoulli spin glass Hamiltonians. We observed that the SCA performed better than the Glauber dynamics in some special cases, while the $\varepsilon$-SCA showed the highest performance in all scenarios.

math.OC↗