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.

168,695 papers · 148 categories

Trend · papers per month

213426639852 · Jun 202019922001200920172026
48 results for trust region optimization

Bayesian optimization tackles constrained high-dimensional problems with penalties and trust regions.

problem Constrained optimization in high-dimensional black-box settings with expensive evaluations and complex feasibility regions.
method Penalty formulation, surrogate model, trust region strategy, Expected Improvement acquisition function.
result The proposed Trust Region method identifies high-quality feasible solutions with fewer evaluations and maintains stable performance.

AdaScale-TuRBO improves high-dimensional Bayesian optimization by dynamically scaling the GP lengthscale.

problem Inappropriate lengthscale design in TuRBO's local GP model causes suboptimal performance in high dimensions.
method Proposes AdaScale-TuRBO, which scales the GP lengthscale with both problem dimension and trust region size.
result AdaScale-TuRBO robustly outperforms standard TuRBO and other methods on synthetic and real-world tasks.

Proposes a new algorithm for solving optimization problems with stochastic objectives and equality constraints.

problem Optimization problems with stochastic objectives and deterministic equality constraints.
method Trust-region stochastic sequential quadratic programming (TR-StoSQP) with adaptive relaxation techniques.
result Established a global almost sure convergence guarantee for TR-StoSQP.

TREGO improves EGO for global optimization of high-dimensional problems.

problem Efficient Global Optimization struggles with high dimensions and lacks theoretical guarantees.
method TREGO alternates between EGO steps and local steps within a trust region.
result TREGO outperforms EGO and other methods in black-box optimization problems.

We propose a trust region method for policy optimization that employs Quasi-Newton approximation for the Hessian, called Quasi-Newton Trust Region Policy Optimization QNTRPO. Gradient descent is the de facto algorithm for reinforcement learning tasks with continuous controls. The algorithm has achieved state-of-the-art…

2019-12-26abs ↗pdf ↗

TROLL improves RL for LLMs by replacing clipping with a trust region projection.

problem Clipping in RL for LLMs causes instability and suboptimal performance.
method TROLL uses a discrete differentiable trust region projection to replace clipping, balancing computational cost and effectiveness.
result TROLL consistently outperforms PPO-like clipping in training speed, stability, and final success rates.

We propose to improve trust region policy search with normalizing flows policy. We illustrate that when the trust region is constructed by KL divergence constraints, normalizing flows policy generates samples far from the 'center' of the previous policy iterate, which potentially enables better exploration and helps av…

2018-09-27abs ↗pdf ↗

The paper analyzes and improves a deep learning optimization technique using matrix gradient orthogonality.

problem Improving deep learning training through more effective optimization methods.
method Develops a stochastic non-Euclidean trust-region gradient method for deep learning optimization.
result Proves state-of-the-art convergence results for the proposed algorithm in various scenarios.

Proximal policy optimization (PPO) is one of the most popular deep reinforcement learning (RL) methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, as a model-free RL method, the success of PPO relies heavily on the effectiveness of its exploratory policy search. In this pa…

2019-01-29abs ↗pdf ↗

New method solves stochastic optimization problems with random models.

problem Optimizing stochastic objectives with deterministic constraints.
method Trust-Region Sequential Quadratic Programming with random model.
result Global convergence guarantees for first- and second-order stationary points.

Adaptive replication improves stochastic function optimization.

problem Challenges in accurately estimating functions with high variance.
method Trust-region-based Bayesian optimization with adaptive replication.
result Adaptive replication substantially improves solution accuracy and efficiency.

Two new algorithms solve nonconvex-strongly concave problems efficiently.

problem Solving nonconvex-strongly concave minimax problems.
method Proposed MINIMAX-TR and MINIMAX-TRACE algorithms.
result Find (ε,ε)(ε, \sqrtε)-second order stationary points within O(ε1.5)\mathcal{O}(ε^{-1.5}) iterations.

End-to-end pipeline for data-driven decision making in mixed-integer optimization.

problem Data-driven decision making in mixed-integer optimization with uncertainty.
method Exploiting mixed-integer optimization-representability of machine learning methods, characterizing decision trust regions, and ensembling multiple models.
result Framework generates high-quality prescriptions and controls model robustness.

Enhances BO in high dimensions with Newton methods.

problem Challenges in scaling BO to high-dimensional spaces.
method Construct multiple local quadratic models using gradients and Hessians from a global GP, and select new sample points by solving bound-constrained quadratic programs.
result Outperforms existing high-dimensional BO techniques on synthetic and real-world applications.

Trust-region methods have yielded state-of-the-art results in policy search. A common approach is to use KL-divergence to bound the region of trust resulting in a natural gradient policy update. We show that the natural gradient and trust region optimization are equivalent if we use the natural parameterization of a st…

2019-02-07abs ↗pdf ↗

New method solves optimization problems with stochastic objectives and constraints.

problem Optimization problems with stochastic objectives and deterministic constraints.
method Trust-region interior-point stochastic sequential quadratic programming (TR-IP-SSQP) method.
result Global almost-sure convergence to first-order stationary points under standard assumptions.

Proximal policy optimization (PPO) is one of the most successful deep reinforcement-learning methods, achieving state-of-the-art performance across a wide range of challenging tasks. However, its optimization behavior is still far from being fully understood. In this paper, we show that PPO could neither strictly restr…

2019-03-19abs ↗pdf ↗

Reinforcement Learning(RL) with sparse rewards is a major challenge. We propose \emph{Hindsight Trust Region Policy Optimization}(HTRPO), a new RL algorithm that extends the highly successful TRPO algorithm with \emph{hindsight} to tackle the challenge of sparse rewards. Hindsight refers to the algorithm's ability to l…

2019-07-29abs ↗pdf ↗

TRM improves long-horizon LLM RL by masking divergent sequences.

problem Long-horizon reinforcement learning with LLMs suffers from off-policy mismatch and approximation errors.
method Derives and applies trust region bounds to control divergence, proposing Trust Region Masking.
result First non-vacuous monotonic improvement guarantees for long-horizon LLM-RL.

TRM improves long-horizon reinforcement learning for LLMs by masking divergent sequences.

problem Long-horizon reinforcement learning for LLMs suffers from off-policy mismatch and approximation errors.
method Derives and applies trust region bounds to control divergence, proposing Trust Region Masking.
result First non-vacuous monotonic improvement guarantees for long-horizon LLM-RL.

Safe RL for autonomous vehicles using PCPO with trust regions and parallel learners.

problem Unexplainable behaviours and lack of safety guarantees in RL for real vehicles.
method PCPO framework with trust regions and parallel learners.
result Safe learning confirmed for autonomous vehicles with fast convergence.

LOL-BO improves latent space Bayesian optimization over structured inputs.

problem Optimizing complex functions over high-dimensional, structured search spaces.
method Adapting trust regions from high-dimensional to structured settings, using a DAE to map inputs into a latent space.
result Achieves up to 20x improvement over state-of-the-art methods.

Success conditioning optimizes policies by imitating successful trajectories, solving a trust-region optimization problem.

problem Improving policies through random actions that lead to desired outcomes.
method Success conditioning, which involves collecting and updating policies based on successful trajectories.
result Success conditioning solves a trust-region optimization problem, maximizing policy improvement with a χ2χ^2 divergence constraint.

A new method improves SVI for high-dimensional, poorly-conditioned distributions.

problem Challenges in existing SVI methods for high-dimensional, poorly-conditioned distributions.
method Trust-region optimization approach leveraging conditional independences and second-order information.
result Superior numerical performance and better scalability in high-dimensional distributions.

Recent advances in policy gradient methods and deep learning have demonstrated their applicability for complex reinforcement learning problems. However, the variance of the performance gradient estimates obtained from the simulation is often excessive, leading to poor sample efficiency. In this paper, we apply the stoc…

2017-10-17abs ↗pdf ↗

Deep Neural Networks are quite vulnerable to adversarial perturbations. Current state-of-the-art adversarial attack methods typically require very time consuming hyper-parameter tuning, or require many iterations to solve an optimization based adversarial attack. To address this problem, we present a new family of trus…

2018-12-16abs ↗pdf ↗

VaR-CPO optimizes VaR-constrained RL problems with conservative policy updates.

problem Optimizing VaR-constrained reinforcement learning problems.
method Combines Cantelli's inequality and trust-region framework for efficient and conservative optimization.
result Achieves zero constraint violations during training in feasible environments.

Canary optimizes VaR-constrained RL problems with a conservative bound using Cantelli's inequality.

problem Optimizing reinforcement learning policies under VaR constraints in dense cost regimes.
method Employing Cantelli's inequality to create a conservative and smooth bound on VaR constraints based on moments of cost returns. Extending trust-region framework for worst-case bounds on policy improvement and constraint violation.
result Canary reliably satisfies VaR constraints with fewest violations and earliest permanent satisfaction, while maintaining reward competitiveness.

Improves inference-time alignment for diffusion models without updating weights.

problem Aligning diffusion models without updating weights for high-reward outputs.
method Trust-Region Iterative Twisted Sequential Monte Carlo (TRI-TSMC) for variance reduction and efficiency.
result Improves primary alignment objectives on text generation tasks.

The paper introduces a method for fitting complex models using simulation and optimization.

problem Fitting models with intractable likelihood or moments.
method Sequential sampling and local smoothing, combining global and local search phases.
result The proposed method outperforms alternative approaches in fitting complex models.

Study shows code-level optimizations significantly impact deep RL algorithms.

problem Understanding the impact of implementation details on deep RL algorithms.
method Case study on PPO and TRPO, investigating the effects of code-level optimizations.
result Code-level optimizations are crucial for performance in deep RL algorithms.

In data-limited settings, stochastic policies can outperform deterministic ones in bandit problems.

problem Making reliable decisions with limited data in bandit problems.
method Designing TRUST, an algorithm that uses localization laws and relative pessimism.
result TRUST achieves comparable sample complexity to LCB on minimax problems but is significantly lower on few-sample problems.