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.
VES-Gamma adapts EI using information-theoretic principles.
JES optimizes expensive functions by considering joint entropy over input and output spaces.
Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the of the unknown function; yet, both are plagued by the expensive computatio…
The scientific method relies on the iterated processes of inference and inquiry. The inference phase consists of selecting the most probable models based on the available data; whereas the inquiry phase consists of using what is known about the models to select the most relevant experiment. Optimizing inquiry involves …
Paper proposes a policy-search algorithm to learn entropy-maximizing exploration policies in reward-free environments.
Unified framework connects EI and information-theoretic acquisition functions.
This paper studies an entropy-based multi-objective Bayesian optimization (MBO). The entropy search is successful approach to Bayesian optimization. However, for MBO, existing entropy-based methods ignore trade-off among objectives or introduce unreliable approximations. We propose a novel entropy-based MBO called Pare…
LES optimizes designs by sampling descent sequences, achieving strong sample efficiency.
A new algorithm learns MAGs from data more efficiently using entropy.
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…
We propose a novel information-theoretic approach for Bayesian optimization called Predictive Entropy Search (PES). At each iteration, PES selects the next evaluation point that maximizes the expected information gained with respect to the global maximum. PES codifies this intractable acquisition function in terms of t…
RES improves robustness in Bayesian optimization.
Contextual policy search allows adapting robotic movement primitives to different situations. For instance, a locomotion primitive might be adapted to different terrain inclinations or desired walking speeds. Such an adaptation is often achievable by modifying a small number of hyperparameters. However, learning, when …
A framework for efficient multi-objective optimization using entropy search.
MESMOC optimizes constrained multi-objective problems efficiently.
Improves neural network search in combinatorial spaces of mathematical symbols.
Improved MESMOC+ optimizes constrained multi-objective problems efficiently.
A new acquisition function RMES improves Bayesian optimization performance.
DE-QT detects optimal Q-learning stopping points.
Bayesian optimization (BO) is a model-based approach to sequentially optimize expensive black-box functions, such as the validation error of a deep neural network with respect to its hyperparameters. In many real-world scenarios, the optimization is further subject to a priori unknown constraints. For example, training…
An energy based approach for stabilizing a mechanical system has offered a simple yet powerful control scheme. However, since it does not impose such strong constraints on parameter space of the controller, finding appropriate parameter values for an optimal controller is known to be hard. This paper intends to generat…
This paper generalizes BO uncertainty measures using decision-theoretic entropies.
A new method for multi-objective Bayesian optimization using entropy search and variational lower bound maximization.
Framework uses optimal transport for neural architecture search.
Bayesian search optimizes exploration of feasible solutions under expensive constraints.
This work presents PESMOC, Predictive Entropy Search for Multi-objective Bayesian Optimization with Constraints, an information-based strategy for the simultaneous optimization of multiple expensive-to-evaluate black-box functions under the presence of several constraints. PESMOC can hence be used to solve a wide range…
TES optimizes black-box functions efficiently with minimal approximations.
We consider the problem of robust optimization within the well-established Bayesian optimization (BO) framework. While BO is intrinsically robust to noisy evaluations of the objective function, standard approaches do not consider the case of uncertainty about the input parameters. In this paper, we propose Noisy-Input …
Improved MORE algorithm reduces regret in black-box optimization and RL tasks.
GIBBON unifies Bayesian optimization for various problem types.
Improving Bayesian Optimization via Training-Aware Conditional Diffusion Models
We develop parallel predictive entropy search (PPES), a novel algorithm for Bayesian optimization of expensive black-box objective functions. At each iteration, PPES aims to select a batch of points which will maximize the information gain about the global maximizer of the objective. Well known strategies exist for sug…
In quadruped gait learning, policy search methods that scale high dimensional continuous action spaces are commonly used. In most approaches, it is necessary to introduce prior knowledge on the gaits to limit the highly non-convex search space of the policies. In this work, we propose a new approach to encode the symme…
We propose minimum regret search (MRS), a novel acquisition function for Bayesian optimization. MRS bears similarities with information-theoretic approaches such as entropy search (ES). However, while ES aims in each query at maximizing the information gain with respect to the global maximum, MRS aims at minimizing the…
CAGES optimizes expensive RL problems by efficiently learning gradients from multiple sources.
We trace the initiative by Professor Meghnad Saha to develop a (statistical) physics model of market economy and his search for the mechanism to constrain the entropy maximized width of the income distribution in a society such that the spread of inequality can be minimized.
Parallel BO method for multi-objective optimization with constraints.
Direct contextual policy search methods learn to improve policy parameters and simultaneously generalize these parameters to different context or task variables. However, learning from high-dimensional context variables, such as camera images, is still a prominent problem in many real-world tasks. A naive application o…
Proposes a link between randomness and compression in deep learning.
A new method for multi-objective Bayesian optimization.
In a standard setting of Bayesian optimization (BO), the objective function evaluation is assumed to be highly expensive. Multi-fidelity Bayesian optimization (MFBO) accelerates BO by incorporating lower fidelity observations available with a lower sampling cost. In this paper, we focus on the information-based approac…
Protein Thoughts interprets protein interactions with clear reasoning, improving prediction accuracy.
Paper introduces MPES for top-k ranking BO with preferential observations.
Bayesian optimization is a sample-efficient method for black-box global optimization. How- ever, the performance of a Bayesian optimization method very much depends on its exploration strategy, i.e. the choice of acquisition function, and it is not clear a priori which choice will result in superior performance. While …
Bayesian optimization methods improved for min max optimization problems.
Unknown constraints arise in many types of expensive black-box optimization problems. Several methods have been proposed recently for performing Bayesian optimization with constraints, based on the expected improvement (EI) heuristic. However, EI can lead to pathologies when used with constraints. For example, in the c…
We present a novel synthesis of Fisher information and asset pricing theory that yields a practical method for reconstructing the probability density implicit in security prices. The Fisher information approach to these inverse problems transforms the search for a probability density into the solution of a differential…
We introduce a novel Entropy-driven Monte Carlo (EdMC) strategy to efficiently sample solutions of random Constraint Satisfaction Problems (CSPs). First, we extend a recent result that, using a large-deviation analysis, shows that the geometry of the space of solutions of the Binary Perceptron Learning Problem (a proto…