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.
Adaptive batching improves Gaussian process surrogates for noisy level set estimation.
problem Learning the level set of noisy simulator responses.
method Developed four novel adaptive batching schemes for Gaussian process metamodels.
result Adaptive batching brings significant computational speed-ups with minimal loss of modeling fidelity.
Replicates and improves Uniswap V3 model using DDQN and Mamba.
problem Improving liquidity provision in Uniswap V3 with reinforcement learning.
method Combines DDQN with Mamba and introduces a new reward function.
result Shows stronger theoretical support and better performance than original model.
By the classical Martingale Representation Theorem, replication of random vectors can be achieved via stochastic integrals or solutions of stochastic differential equations. We introduce a new approach to replication of random vectors via adapted differentiable processes generated by a controlled ordinary differential …
Optimizing expensive black-box systems with limited data is an extremely challenging problem. As a resolution, we present a new surrogate optimization approach by addressing two gaps in prior research -- unimportant input variables and inefficient treatment of uncertainty associated with the black-box output. We first …
Recent advances in smart cities applications enforce security threads such as node replication attacks. Such attack is take place when the attacker plants a replicated network node within the network. Vehicular Ad hoc networks are connecting sensors that have limited resources and required the response time to be as lo…
The paper proposes a method to adapt machine learning models to changing conditions.
problem Machine learning models need to adapt to new conditions in a constantly changing environment.
method Reuse knowledge from existing models to train future generations.
result The proposed method allows machine learning models to adapt and survive in a dynamic environment.
Study replicability in high-dimensional statistics, resolving open problems.
problem Ensuring consistent results in high-dimensional statistical tasks.
method Introduced replicable learning algorithms and established computational and statistical equivalence with high-dimensional isoperimetric tilings.
result Matching sample complexity upper and lower bounds for replicable mean estimation and coin problem.
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…
We report successful results from using deep learning neural networks (DLNNs) to learn, purely by observation, the behavior of profitable traders in an electronic market closely modelled on the limit-order-book (LOB) market mechanisms that are commonly found in the real-world global financial markets for equities (stoc…
Study uses deep learning for pairs trading in Polish equities, achieving profits in 2017-2019.
problem Statistical arbitrage in Polish equities market using traditional methods.
method Deep learning (LSTMs) for asset replication, PCA for risk factor analysis, Ornstein Uhlenbeck process for residual modeling.
result Deep learning methods, especially LSTMs, show promise for profitable trading in Polish equities.
The chapter compares Gaussian process models for stochastic simulators with varying noise.
problem Modeling stochastic simulators with varying noise.
method Various Gaussian process models are compared, including input varying noise variance, non-Gaussian noise, and quantile modeling.
result Sequential design procedures are adapted for these models.
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechanism in the framework of metalearning, where the aim is to replicate some of the flexibility of human …
New algorithm ensures consistent results in constrained MAB problems.
problem Achieving consistent results in constrained MAB problems.
method Developed replicable algorithms for constrained MAB problems using the optimism principle.
result Regret and constraint violation of replicable algorithms match those of non-replicable ones.
Unified framework for fixed-income pricing and liability replication.
problem Static arbitrage and discount curve construction.
method Model-free framework for static fixed-income pricing and liability replication.
result Existence of strictly positive discount curves reproducing market prices and least-cost super-replicating portfolios.
Characterizes super-replication prices in a financial market model.
problem Characterizing prices in a financial market model.
method Characterizes prices as the supremum of mono-prior super-replication prices through extreme priors and martingale measures.
result Super-replication prices are the supremum of mono-prior super-replication prices.
New study on replicability and stability in machine learning algorithms.
problem Ensuring consistent results in machine learning models without fixing randomness.
method Introduced global stability and list replicability concepts, proving their equivalence and boosting list replicability.
result Global stability can only be achieved weakly, while list replicability can be boosted to achieve high probability of consistent results.
Study on computational aspects of replicable learning, bridging statistical and algorithmic perspectives.
problem Understanding the computational connections between replicability and various learning paradigms.
method Design of replicable learners, lifting framework, and transformation techniques.
result Efficient replicable learners for specific learning problems under various distributions.
The paper classifies self-replicating 3D shapes using algebraic models.
problem Understanding self-replicating 3D shapes.
method Using idempotents in the (2+1)-cobordism category to classify 3-manifolds.
result A classification theorem for self-replicating 3-manifolds.
Undirected graphs can be used to describe matrix variate distributions. In this paper, we develop new methods for estimating the graphical structures and underlying parameters, namely, the row and column covariance and inverse covariance matrices from the matrix variate data. Under sparsity conditions, we show that one…
Model financial network dynamics to avoid systemic risk.
problem Emergence of systemic risk in financial networks.
method Derive solutions of random fixed point equations, analyze replicator dynamics, derive conditions for evolutionary stable strategies, verify with simulations.
result Emerging strategies converge to an attractor of an ODE, avoiding systemic risk.
New algorithm prevents strategic replication in multi-armed bandit problems.
problem Strategic replication by agents can exploit bandit algorithms' balance.
method Designs Hierarchical UCB (H-UCB) and Robust Hierarchical UCB (RH-UCB) algorithms.
result Achieves O(lnT)-regret and sublinear regret in realistic scenarios. Extends super-replication theorem with dynamic strategies and transaction costs.
problem Dynamic super-replication under proportional transaction costs.
method Generalizes admissible strategies and defines a well-defined super-replication price process.
result Well-defined super-replication price process in dynamic setting.
Study reveals statistical bias in dataset replication, reducing accuracy drop from 11-14% to 3.6%.
problem Statistical bias in dataset replication affects model generalization accuracy.
method Analyzed ImageNet-v2, identified and corrected for bias, and compared results.
result Correcting bias reduces accuracy drop from 11-14% to 3.6%.
Model financial network dynamics to avoid systemic risk.
problem Avoid systemic risk in financial networks.
method Model financial network as random liability graph, agents adapt strategies based on learning, analyze using ODE.
result Emerging strategies converge to evolutionary stable strategies (all risky or all less risky agents).
New uniformity tester ensures consistent results across different samples.
problem Non-replicable behavior of uniformity testing algorithms.
method Develops a replicable uniformity tester with improved sample complexity.
result Achieves nearly linear dependence on replicability factor ρ. ERICA assesses replicability of cluster analysis results.
problem Lack of quantitative scrutiny for clustering results.
method ERICA: a framework to assess replicability of cluster analysis.
result Clusters are found to be replicable in synthetic data but not in real-world datasets.
In this work we introduce the notion of fully incomplete markets. We prove that for these markets the super-replication price coincide with the model free super-replication price. Namely, the knowledge of the model does not reduce the super-replication price. We provide two families of fully incomplete models: stochast…
Detects backdoors in outsourced models by replicating training steps across multiple servers.
problem Detecting backdoors in models trained on cloud providers without prior knowledge.
method Replicate training steps across multiple servers to identify deviations and malicious updates.
result 99.6% accuracy in identifying backdoored models out of 50% malicious providers.
We study super--replication of contingent claims in markets with fixed transaction costs. This can be viewed as a stochastic impulse control problem with a terminal state constraint. The first result in this paper reveals that in reasonable continuous time financial market models the super--replication price is prohibi…
Replicable clustering algorithms for k-medians, k-means, and k-centers are proposed.
problem Designing clustering algorithms that produce the same partition on repeated runs under the same distribution.
method Utilizing approximation routines for combinatorial clustering problems in a black-box manner.
result Replicable algorithms for statistical k-medians, k-means, and k-centers with specified approximation and sample complexities. In this paper we propose a new robust algorithm to find the optimal static replicating portfolios for general nonlinear payoff functions and give the estimate of the rate of convergence that is absent in the literature. We choose the static replication by minimizing the error bound between the nonlinear payoff function…
ACFS optimizes spectral risk under decision-dependent uncertainty using adaptive forest sampling.
problem Minimizing spectral risk with decision-dependent uncertainty.
method ACFS integrates Generalised Random Forests, CEM-guided exploration, rank-weighted augmentation, and multi-start refinement.
result ACFS achieves lowest median oracle spectral risk on both benchmarks.
The paper prices long-term options with a reflecting barrier model.
problem Pricing long-term options with asset price limits.
method Model asset price as geometric Brownian motion with a lower reflecting barrier, pricing options using compound options.
result Option prices can be determined using standard risk-neutral arguments, and hedging strategies are available.
New RL algorithm ensures stable, replicable policies.
problem Stability and replicability issues in RL algorithms.
method Introduced weak and strong forms of list replicability, developed a novel planning strategy, and tested state reachability.
result Proved efficient tabular RL algorithm with polynomial list complexity.
Study on replicability in reinforcement learning algorithms.
problem Ensuring consistent policy outputs in reinforcement learning.
method Mathematical study focusing on replicability in discounted tabular MDPs with a generative model.
result Design of efficient replicable and TV indistinguishable algorithms for policy estimation.
Efficient algorithms improve learning of large-margin halfspaces.
problem Learning large-margin halfspaces efficiently and reproducibly.
method Design of efficient, dimension-independent, polynomial-time algorithms; SGD-based approach; DP-to-Replicability reduction.
result Improved sample complexity compared to previous algorithms, with optimal sample complexity for one algorithm.
The implementation of the Own Risk and Solvency Assessment is a critical issue raised by Pillar II of Solvency II framework. In particular the Overall Solvency Needs calculation left the Insurance companies to define an optimal entity-specific solvency constraint on a multi-year time horizon. In a life insurance societ…
This paper studies robust payoff allocation in submodular games, especially against replication.
problem Payoff allocation in submodular games, especially robustness against replication.
method Systematically studied replication manipulation in submodular games, introduced replication robustness metric, and validated with empirical ML data market.
result Conditions characterizing robustness of semivalues in submodular games.
We describe TF-Replicator, a framework for distributed machine learning designed for DeepMind researchers and implemented as an abstraction over TensorFlow. TF-Replicator simplifies writing data-parallel and model-parallel research code. The same models can be effortlessly deployed to different cluster architectures (i…
The study examines a financial model with sticky prices and finds no arbitrage when interest rate is zero.
problem Analyzing financial markets with sticky asset prices and proving no arbitrage conditions.
method Introduced a financial market model with a risky asset following a sticky geometric Brownian motion and a riskless asset with a constant interest rate. Proved no arbitrage conditions and derived pricing equations.
result No arbitrage conditions are met only when the interest rate is zero, and all replicable payoffs are derived under this condition.
We develop a unified valuation theory that incorporates credit risk (defaults), collateralization and funding costs, by expanding the replication approach to a generality that has not yet been studied previously and reaching valuation when replication is not assumed. This unifying theoretical framework clarifies the re…
Adapts Monte Carlo method to price π-options related to maximum drawdown.
problem Pricing π-options in volatile market conditions.
method Monte Carlo algorithm with simulated price tree.
result Algorithm produces bounds converging to true price with tree depth.
New algorithm ensures replicable results in multi-armed bandits with minimal extra regret.
problem Ensuring consistent results in multi-armed bandit studies.
method Incorporates randomness into decision-making to ensure replicability while maintaining minimal extra regret.
result For large time horizons, proposed algorithm suffers only K2/ρ2 times smaller amount of exploration than existing algorithms. Study models interest rates as CTMC, pricing and replicating derivatives.
problem Modeling and pricing financial derivatives in a CTMC setting.
method Model short rate as CTMC, derive pricing and replication strategies, apply Ross Recovery Theorem.
result Derive real-world dynamics of CTMC.
A study shows that a fine-tuned model's directional accuracy in financial forecasting is largely due to chance, not skill.
problem Misleading directional accuracy in financial forecasting models.
method A reproducible, frozen-data benchmark with paired significance tests to separate skill from base-rate artifact.
result Fine-tuned models do not show significant directional skill over a base rate of 70% in financial forecasting.
Knockoffs method selects financial factors, controlling false discoveries.
problem Controlling false discoveries in financial factor selection.
method Apply knockoff procedure to build fake factors.
result Shows versatility in fund replication and network inference.
Study liquidity provision in decentralized exchanges considering risk aversion and replication costs.
problem Economic viability of liquidity provision in decentralized exchanges (DEXs).
method Formulated strategic interactions as a sequential game with risk-averse LP, traders, and arbitrageurs.
result DEX liquidity depth is crucial for risk management, influenced by risk aversion and replication costs.