Boltzmann exploration is widely used in reinforcement learning to provide a trade-off between exploration and exploitation. Recently, in (Cesa-Bianchi et al., 2017) it has been shown that pure Boltzmann exploration does not perform well from a regret perspective, even in the simplest setting of stochastic multi-armed b…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Boltzmann exploration”
A new method for fitting mixture models using Boltzmann exploration.
problem Challenges in learning mixture models, especially with good initialisation.
method Boltzmann exploration expectation-maximisation (BEEM) algorithm.
result BEEM can escape local optima and is insensitive to parameter initialisation.
Quantum Boltzmann Machines trained on quantum annealers produce noisy synthetic data.
problem Training quantum Boltzmann machines on quantum annealers for financial data generation.
method Used D-Wave Advantage 4.1 quantum annealer to train QBMs and compare with classical RBMs.
result Quantum Boltzmann Machines trained on quantum annealers are noisier and less effective than classical RBMs.
Boltzmann exploration is a classic strategy for sequential decision-making under uncertainty, and is one of the most standard tools in Reinforcement Learning (RL). Despite its widespread use, there is virtually no theoretical understanding about the limitations or the actual benefits of this exploration scheme. Does it…
New method uses RBM flows to find critical temperatures in Ising models.
problem Detecting critical temperatures in RBM flows without model topology information.
method Iterative sampling from RBM mapped on Ising model temperature space using a neural network thermometer.
result Flow of RBM trained on Ising spin configurations approaches critical temperature around .
Boltzmann-Gibbs Distribution of Fortune and Broken Time-Reversible Symmetry in Econodynamicsphysics.soc-ph
Within the description of stochastic differential equations it is argued that the existence of Boltzmann-Gibbs type distribution in economy is independent of the time reversal symmetry in econodynamics. Both power law and exponential distributions can be accommodated by it. The demonstration is based on a mathematical …
Paper explores Monge-Ampère in deep learning and quantum geometry.
problem Understanding the Monge-Ampère equation in deep learning.
method Review of Boltzmann learning, connection to optimal transport, insights from quantum geometry, renormalization group flow.
result Space of covariance matrices in learning dynamics coincides with the CAH cone.
MEMEC improves sample efficiency in reinforcement learning.
problem Lack of sample efficiency in reinforcement learning.
method Proposes MEMEC, a Boltzmann policy with state-dependent temperature for more principled exploration.
result MEMEC outperforms other methods on classic RL environments and Atari games.
Generative Kernel PCA explores latent spaces for data interpretation and novelty detection.
problem Exploring latent spaces of datasets for better data interpretation.
method Generative Kernel PCA using hidden and visible units similar to Restricted Boltzmann Machines.
result Gradually moving in the latent space allows for interpretation of components and detection of novel patterns.
We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as …
SPAQL improves RL by adaptively partitioning state-action space and learning a time-invariant policy.
problem Efficient model-free reinforcement learning with scalable algorithms.
method Adaptive Q-learning with UCB and Boltzmann exploration, automatically tuning temperature.
result SPAQL converges faster and uses fewer resources than AQL, showing higher sample efficiency.
Quantum annealing (QA) is a hardware-based heuristic optimization and sampling method applicable to discrete undirected graphical models. While similar to simulated annealing, QA relies on quantum, rather than thermal, effects to explore complex search spaces. For many classes of problems, QA is known to offer computat…
We consider the problem of classification when inputs correspond to sets of vectors. This setting occurs in many problems such as the classification of pieces of mail containing several pages, of web sites with several sections or of images that have been pre-segmented into smaller regions. We propose generalizations o…
From Monte Carlo to Las Vegas: Improving Restricted Boltzmann Machine Training Through Stopping Setscs.LG
We propose a Las Vegas transformation of Markov Chain Monte Carlo (MCMC) estimators of Restricted Boltzmann Machines (RBMs). We denote our approach Markov Chain Las Vegas (MCLV). MCLV gives statistical guarantees in exchange for random running times. MCLV uses a stopping set built from the training data and has maximum…
We propose randomized least-squares value iteration (RLSVI) -- a new reinforcement learning algorithm designed to explore and generalize efficiently via linearly parameterized value functions. We explain why versions of least-squares value iteration that use Boltzmann or epsilon-greedy exploration can be highly ineffic…
This paper investigates the effectiveness of adversarial training in enhancing the robustness of Deep Q-Network (DQN) policies to state-space perturbations. We first present a formal analysis of adversarial training in DQN agents and its performance with respect to the proportion of adversarial perturbations to nominal…
The study analyzes the evolution of Gaussian measures under a specific gradient flow.
problem Analyzing the evolution of Gaussian measures under a specific gradient flow.
method Derives ordinary differential equations governing the evolution of mean, covariance, and mass under the HK-Boltzmann gradient flow.
result Exponential convergence to equilibrium demonstrated through Polyak-Lojasiewicz-type inequalities.
Market lawsq-fin.ST
Power laws detected in financial data, modeled with random multipliers.
problem Detecting power laws in financial data.
method Investigated data from financial instruments, proposed a model based on sums of Maxwell-Boltzmann distributions with random multipliers.
result Detected power laws with various exponents in financial data, proposed a universal model.
Transferable Boltzmann Generators learn to sample unseen molecules efficiently.
problem Generating equilibrium samples of molecular systems.
method Boltzmann Generators using normalizing flows to learn transformations.
result Transferable Boltzmann Generators can predict zero-shot Boltzmann distributions for unseen molecules.
The paper uses machine learning to simulate financial markets and improve trading strategy backtesting.
problem Improving risk management of quantitative investment strategies.
method Simulates financial markets using Boltzmann Machines and Generative Adversarial Networks to preserve asset return distributions and dependencies.
result Developed a framework to estimate backtest statistics more accurately.
D-Wave computers struggle with sampling Boltzmann distributions efficiently.
problem Sampling Boltzmann distributions efficiently on D-Wave computers.
method Exploring various obstacles and remaining difficulties.
result Challenges remain in using D-Wave computers for efficient sampling.
Improved online Q-learning for MDPs with concentration bounds.
problem Online Q-learning in infinite-horizon discounted MDPs with sublinear regret for large gaps.
method Smoothed -Greedy exploration scheme combining -greedy and Boltzmann exploration, analyzed using concentration bounds for contractive Markovian stochastic approximation.
result Near- regret bound for Smoothed -Greedy exploration scheme.
We present transductive Boltzmann machines (TBMs), which firstly achieve transductive learning of the Gibbs distribution. While exact learning of the Gibbs distribution is impossible by the family of existing Boltzmann machines due to combinatorial explosion of the sample space, TBMs overcome the problem by adaptively …
The probability density function for the visible sector of a Riemann-Theta Boltzmann machine can be taken conditional on a subset of the visible units. We derive that the corresponding conditional density function is given by a reparameterization of the Riemann-Theta Boltzmann machine modelling the original probability…
We introduce a new method for training deep Boltzmann machines jointly. Prior methods require an initial learning pass that trains the deep Boltzmann machine greedily, one layer at a time, or do not perform well on classifi- cation tasks.
Boltzmann machines as two-dimensional tensor networkscond-mat.stat-mech
RBM and DBM are represented as 2D tensor networks, revealing their expressive power and efficiency.
problem Understanding and optimizing RBM and DBM models.
method Representing RBM and DBM as 2D tensor networks and developing an efficient tensor network contraction algorithm.
result The proposed algorithm for computing partition functions is more accurate than state-of-the-art methods.
iDEM generates samples from Boltzmann densities without data.
problem Generating statistically independent samples from unnormalized distributions.
method Iterative algorithm using energy and gradient for diffusion-based sampler training.
result iDEM achieves state-of-the-art performance and trains faster than existing methods.
A new multi-objective RL framework improves intrinsic exploration performance.
problem Sub-optimal exploration performance due to ad-hoc handling of intrinsic exploration.
method A multi-objective RL framework where both exploration and exploitation are optimized as separate objectives.
result EMU-Q method outperforms classic and other intrinsic RL methods on benchmarks.
A new method speeds up sampling of Boltzmann distribution in high-dimensional systems.
problem High computational cost of obtaining Jacobian of flow-based models in high dimensions.
method Flow perturbation method that incorporates stochastic perturbations and reweighting.
result Achieves unbiased sampling of Boltzmann distribution with orders of magnitude speedup.
We show that deep narrow Boltzmann machines are universal approximators of probability distributions on the activities of their visible units, provided they have sufficiently many hidden layers, each containing the same number of units as the visible layer. We show that, within certain parameter domains, deep Boltzmann…
On a Riemannian manifold, lower Ricci curvature bounds are known to be characterized by geodesic convexity properties of various entropies with respect to the Kantorovich-Rubinstein-Wasserstein square distance from optimal transportation. These notions also make sense in a (nonsmooth) metric measure setting, where they…
Commercial activity trackers are set to become an essential tool in health research, due to increasing availability in the general population. The corresponding vast amounts of mostly unlabeled data pose a challenge to statistical modeling approaches. To investigate the feasibility of deep learning approaches for unsup…
A new machine learning model uses score matching to estimate probability densities efficiently.
problem Estimating probability density functions is challenging.
method Introduced a product Jacobi-Theta Boltzmann machine (pJTBM) and used score matching for efficient fitting.
result The pJTBM can fit probability densities more efficiently than the RTBM using score matching.
Neural Boltzmann Machines improve on CRBMs for modeling data.
problem Limited expressivity of CRBMs with noisy data.
method Convert CRBM parameters to neural networks.
result NBMs can approximate data likelihood better.
This paper provides a tutorial on Boltzmann Machines and Deep Belief Networks.
problem Understanding and applying Boltzmann Machines and Deep Belief Networks.
method Explains the structures, conditional distributions, Gibbs sampling, training methods, and deep belief networks of RBMs.
result Comprehensive overview of RBMs and DBNs, useful in various fields.
New method trains Boltzmann machines without supervision.
problem Training unsupervised learning models.
method Mixed binary quadratic feasibility problem formulation.
result Theory validated on XOR patterns.
Study explores D-Wave QA for RBM training, finds modest benefits but no significant improvements.
problem Improving RBM training using D-Wave quantum annealing.
method Hybrid sampling approach combining classical and D-Wave QA methods.
result No significant improvements in RBM training using D-Wave QA, but potential for CF mitigation.
CAP-BM learns complex-valued data's amplitude and phase distributions.
problem Learning from complex-valued data with amplitude variation.
method Complex Amplitude-Phase Boltzmann machine (CAP-BM) with Gibbs sampling.
result Necessity of amplitude-amplitude coupling term in CAP-BM.
We propose a relaxation-based approximate inference algorithm that samples near-MAP configurations of a binary pairwise Markov random field. We experiment on MAP inference tasks in several restricted Boltzmann machines. We also use our underlying sampler to estimate the log-partition function of restricted Boltzmann ma…
In 1870s, L. Boltzmann proved the famous -theorem for the Boltzmann equation in the kinetic theory of gas and gave the statistical interpretation of the thermodynamic entropy. In 2002, G. Perelman introduced the notion of -entropy and proved the -entropy formula for the Ricci flow. This plays a crucial role in…
Can Boltzmann Machines Discover Cluster Updates ?physics.comp-ph
Boltzmann machines are physics informed generative models with wide applications in machine learning. They can learn the probability distribution from an input dataset and generate new samples accordingly. Applying them back to physics, the Boltzmann machines are ideal recommender systems to accelerate Monte Carlo simu…
New sampler tackles complex discrete energy landscapes efficiently.
problem Stagnation in gradient-based discrete samplers for non-convex settings.
method DREXEL sampler with Replica Exchange and Adjusted Metropolis.
result Proves samplers satisfy detailed balance and converge to target distribution.
Boltzmann machines are powerful distributions that have been shown to be an effective prior over binary latent variables in variational autoencoders (VAEs). However, previous methods for training discrete VAEs have used the evidence lower bound and not the tighter importance-weighted bound. We propose two approaches fo…
A new sampler and temperature estimation method enable efficient learning of Boltzmann Machines.
problem Efficient learning of Boltzmann Machines (BMs) is challenging due to high training costs and difficulty in parallelization.
method Proposed a new Boltzmann sampler (Langevin SB, LSB) and an efficient method (Conditional Expectation Matching, CEM) for estimating inverse temperature.
result Established an efficient learning framework (Sampler-Adaptive Learning, SAL) for BMs with greater expressive power than Restricted Boltzmann Machines (RBMs).
In this work we present a novel approach for transfer-guided exploration in reinforcement learning that is inspired by the human tendency to leverage experiences from similar encounters in the past while navigating a new task. Given an optimal policy in a related task-environment, we show that its bisimulation distance…
EDG generates Boltzmann samples from latent variables efficiently.
problem Sampling from complex energy functions in high dimensions.
method Combines variational autoencoders and diffusion models; uses a decoder and diffusion-based encoder.
result EDG outperforms existing methods in various sampling tasks.
A Gaussian restricted Boltzmann machine (GRBM) is a Boltzmann machine defined on a bipartite graph and is an extension of usual restricted Boltzmann machines. A GRBM consists of two different layers: a visible layer composed of continuous visible variables and a hidden layer composed of discrete hidden variables. In th…
BNEM improves Boltzmann sampler efficiency.
problem Generating IID samples from Boltzmann distributions efficiently.
method Bootstrapped Noised Energy Matching (NEM) combined with diffusion-based learning and bootstrapping.
result BNEM achieves state-of-the-art performance with improved robustness.