Research
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.

168,657 papers · 148 categories

Trend · papers per month

51102152203 · Jun 202019922001200920172026
48 results for softmax policy

Softmax PG methods can take extremely long to converge, even with exact gradients.

problem Softmax policy gradient methods can take an impractically long time to converge in reinforcement learning.
method Softmax policy gradient methods with exact gradient computation.
result Softmax PG methods can take exponential number of iterations to converge, even with optimal initialization.

Softmax policy gradient achieves global optimality in wide neural networks with entropy regularization.

problem Optimizing softmax policies with neural networks in the mean-field regime.
method Modeling neural networks as Wasserstein gradient flows and proving global optimality of fixed points.
result Global optimality of softmax policy gradient in wide single hidden layer neural networks with entropy regularization.

Softmax policy gradient methods converge at O(1/t)O(1/t) rate with constants depending on problem and initialization.

problem Understanding convergence rates of softmax policy gradient methods in tabular settings.
method Analysis of softmax policy gradient and entropy regularized policy gradient methods, using Łojasiewicz inequality and lower bounds.
result Entropy regularization improves convergence rate from O(1/t)O(1/t) to O(ect)O(e^{-c \cdot t}).

Entropy regularization improves policy optimization in reinforcement learning.

problem Improving policy optimization in reinforcement learning.
method Entropy regularization is introduced to soften the greedy policy towards a more diverse softmax policy, leading to a continuously parameterized algorithm that interpolates between policy gradient and Q-learning.
result An intermediate algorithm can improve performance in reinforcement learning.

Large deviations theory applied to policy gradient methods.

problem Understanding convergence of policy gradient methods in reinforcement learning.
method Large deviation rate function and contraction principle from large deviations theory.
result Convergence properties of policy gradient methods can be extended to various policy parametrizations.

We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization. Specifically, we show that softmax consistent action values correspond to optimal entropy regularized policy pro…

2017-02-28abs ↗pdf ↗

Paper analyzes convergence of dynamic policy gradient for MDPs, improving performance in finite-time problems.

problem Optimal policies in finite-time MDPs are not stationary and require epoch-specific training.
method Introduces dynamic policy gradient combining dynamic programming and policy gradient, analyzes convergence for softmax parametrisation.
result Dynamic policy gradient training exploits finite-time structure, leading to better convergence bounds.

A softmax operator applied to a set of values acts somewhat like the maximization function and somewhat like an average. In sequential decision making, softmax is often used in settings where it is necessary to maximize utility but also to hedge against problems that arise from putting all of one's weight behind a sing…

2016-12-16abs ↗pdf ↗

We study a policy gradient method with L2 regularization for MAB problems.

problem Improving policy gradient methods for MAB problems with regularization.
method Investigate convergence of a policy gradient algorithm with L2 regularization for MAB.
result Prove convergence under appropriate technical hypotheses and show practical improvements.

Policy gradient and actor-critic algorithms form the basis of many commonly used training techniques in deep reinforcement learning. Using these algorithms in multiagent environments poses problems such as nonstationarity and instability. In this paper, we first demonstrate that standard softmax-based policy gradient c…

2019-06-01abs ↗pdf ↗

Linear Q-learning converges to a bounded set without divergence.

problem Proving linear Q-learning does not diverge and converges to a bounded set.
method No modifications to the original linear Q-learning algorithm, no Bellman completeness or near-optimality assumptions, only an ε-softmax behavior policy with adaptive temperature.
result First L2L^2 convergence rate of linear Q-learning iterates to a bounded set.

Interpolates between SPG and NeuRD with Capped Implicit Exploration.

problem Combining SPG and NeuRD for better performance in non-stationary environments.
method Introduces Capped Implicit Exploration (CIX) to interpolate between SPG and NeuRD.
result NeuRD-CIX performs well more consistently than NeuRD while retaining NeuRD's advantages.

Short note on soft-max and policy gradients in bandit problems using Lyapunov functions.

problem Analyzing soft-max and policy gradient methods in bandit problems.
method Lyapunov function argument for soft-max and differential equations for policy gradient algorithms.
result Regret bounds for soft-max and a different policy gradient algorithm in bandit problems.

Exploration policies in Bayesian bandits maximize the average reward over problem instances drawn from some distribution P\mathcal{P}. In this work, we learn such policies for an unknown distribution P\mathcal{P} using samples from P\mathcal{P}. Our approach is a form of meta-learning and exploits properties of $\ma…

2020-02-17abs ↗pdf ↗

We propose expected policy gradients (EPG), which unify stochastic policy gradients (SPG) and deterministic policy gradients (DPG) for reinforcement learning. Inspired by expected sarsa, EPG integrates (or sums) across actions when estimating the gradient, instead of relying only on the action in the sampled trajectory…

2018-01-10abs ↗pdf ↗

Entropy-regularized NPG methods converge linearly in discounted MDPs.

problem Theoretical limitations of NPG methods in reinforcement learning.
method Entropy regularization in conjunction with NPG methods for discounted MDPs.
result Entropy-regularized NPG methods converge linearly in discounted MDPs.

Improved exploration in cooperative multi-agent reinforcement learning.

problem Limited expressiveness of Gaussian policies in DecSPG hinders effective exploration.
method Proposes decentralized diffusion policy learning (DDPL) with denoising diffusion probabilistic models.
result Consistently improved performance on various MARL benchmarks.

Softmax is an output activation function for modeling categorical probability distributions in many applications of deep learning. However, a recent study revealed that softmax can be a bottleneck of representational capacity of neural networks in language modeling (the softmax bottleneck). In this paper, we propose an…

2018-05-28abs ↗pdf ↗

Novel framework for policy optimization with general parameterization and linear convergence.

problem Lack of theoretical guarantees for policy optimization with general parameterization schemes.
method Mirror descent approach for policy optimization with general parameterization.
result First result of linear convergence for policy-gradient-based method with general parameterization.

Paper develops NPG for risk-averse RL with ECRMs, proving global convergence.

problem Ensuring reliable performance in stochastic RL problems with risk-averse policies.
method Developed natural policy gradient updates for ECRMs-based RL problems, proving global optimality and iteration complexity.
result Global convergence of risk-averse NPG algorithm with ECRMs.

The computational cost of training with softmax cross entropy loss grows linearly with the number of classes. For the settings where a large number of classes are involved, a common method to speed up training is to sample a subset of classes and utilize an estimate of the loss gradient based on these classes, known as…

2019-07-24abs ↗pdf ↗

Revises logistic-softmax likelihood for Bayesian meta-learning in few-shot classification.

problem Inherent uncertainty in logistic-softmax leads to suboptimal performance in meta-learning.
method Redesigns logistic-softmax likelihood with a temperature parameter for better control of prior confidence.
result Achieves well-calibrated uncertainty estimates and comparable/superior performance on benchmark datasets.

KL-constrained API shows optimization issues and improved with regularization.

problem Optimization issues in KL-constrained API algorithms.
method Comparison of KL divergence as a constraint vs. regularizer, empirical evaluation.
result KL-constrained API is not guaranteed to converge and incurs linear regret.

Paper introduces Balanced Meta-Softmax for better long-tailed visual recognition.

problem Long-tailed distribution mismatch between training and testing data.
method Balanced Meta-Softmax, an unbiased extension of Softmax, using a Meta Sampler.
result Balanced Meta-Softmax outperforms state-of-the-art solutions on visual recognition and instance segmentation.

End-to-end framework learns LLM routing from observational data.

problem Compounding errors in decoupled approaches and reliance on full-feedback data.
method Causal end-to-end framework minimizing decision-making regret from observational data.
result Method outperforms existing baselines across different embedding models.

Entropy-regularized NPG converges linearly with linear function approximation.

problem Analyzing convergence of entropy-regularized NPG with function approximation.
method Established finite-time convergence analyses with entropy regularization and linear function approximation.
result Entropy-regularized NPG achieves linear convergence up to a function approximation error.

Binary testing for softmax models requires many samples, similar to leverage score models.

problem Binary hypothesis testing for softmax models and leverage score models.
method Analyzing sample complexity and drawing analogies between models.
result Sample complexity is asymptotically \(O(ε^{-2})\), where \(ε\) is the distance between model parameters.

The paper investigates polynomial alternatives to softmax in transformer models.

problem The effectiveness of softmax attention in transformers is questioned.
method The authors explore polynomial activations as alternatives to softmax, focusing on their ability to regularize the attention matrix.
result Certain polynomials can serve as effective substitutes for softmax in transformer applications, achieving strong performance.

Softmax temperature influences model representation rank and performance.

problem Understanding and optimizing softmax function's impact on model representations.
method Investigated softmax function's role in deep neural networks, introduced rank deficit bias.
result Softmax temperature affects model representation rank and can improve performance.

Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a gene…

2016-12-07abs ↗pdf ↗

DR-RPO optimizes robust policies in RL with limited interaction, achieving sublinear regret.

problem Policy optimization in RL under distribution shift and adversarial dynamics.
method DR-RPO algorithm incorporating reference-policy regularization and upper confidence bonus for exploration.
result DR-RPO achieves sublinear regret and polynomial suboptimality bounds in robust RL.

Recent neural network and language models rely on softmax distributions with an extremely large number of categories. Since calculating the softmax normalizing constant in this context is prohibitively expensive, there is a growing literature of efficiently computable but biased estimates of the softmax. In this paper …

2018-03-22abs ↗pdf ↗

Solves challenges in estimating parameters of softmax gating Gaussian mixture models.

problem Identifiability issues and complex interactions in Gaussian mixture of experts.
method Proposes novel Voronoi loss functions and establishes convergence rates of MLE.
result Connects convergence rate of MLE to a solvability problem of polynomial equations.

Study shows policy gradient convergence for entropy-regularized MDPs with neural nets in mean-field regime.

problem Global convergence of policy gradient for entropy-regularized MDPs with neural network approximation.
method Softmax policy with neural network approximation in mean-field regime, gradient flow in 2-Wasserstein metric, exponential convergence under sufficient regularization.
result Gradient flow converges exponentially fast to the unique stationary solution under sufficient regularization.