arXiv research

LLM trading agents show risk feedback can improve alignment without fine-tuning.

New algorithm reduces risk in online games with limited feedback.

Algometrics analyzes how predictive models affect their own forecasts in algorithmic markets.

Study quantile reward identification with 1-bit feedback constraints.

According to the volatility feedback effect, an unexpected increase in squared volatility leads to an immediate decline in the price-dividend ratio. In this paper, we consider the properties of stock price dynamics and option valuations under the volatility feedback effect by modeling the joint dynamics of stock price,…

The goal of counterfactual learning for statistical machine translation (SMT) is to optimize a target SMT system from logged data that consist of user feedback to translations that were predicted by another, historic SMT system. A challenge arises by the fact that risk-averse commercial SMT systems deterministically lo…

We develop a learning principle and an efficient algorithm for batch learning from logged bandit feedback. This learning setting is ubiquitous in online systems (e.g., ad placement, web search, recommendation), where an algorithm makes a prediction (e.g., ad ranking) for a given input (e.g., query) and observes bandit …

The paper addresses learner privacy in convex optimization with feedback.

SetRank tackles collaborative ranking from implicit feedback using setwise Bayesian approach.

Plug-in method improves performative prediction accuracy.

Develops a measure for subjective explainability of ML predictions.

Paper studies CLO with partial feedback, improving decision-making in uncertain contexts.

We study cascades on a two-layer multiplex network, with asymmetric feedback that depends on the coupling strength between the layers. Based on an analytical branching process approximation, we calculate the systemic risk measured by the final fraction of failed nodes on a reference layer. The results are compared with…

Survey examines types of systemic risk in financial networks.

The focal point of this paper is the issue of "drawdown" which arises in recursive betting scenarios and related applications in the stock market. Roughly speaking, drawdown is understood to mean drops in wealth over time from peaks to subsequent lows. Motivated by the fact that this issue is of paramount concern to co…

New framework learns from partial feedback in multi-label tasks.

Risk-aware linear bandits optimize against adverse outcomes.

A simple quantitative example of a reflexive feedback process and the resulting price dynamics after an exogenous price shock to a financial network is presented. Furthermore, an outline of a theory that connects financial reflexivity, which stems from cross-ownership and delayed or incomplete information, and no-arbit…

Proposes a method to train classifiers with delayed feedback using a time window.

Boosting for off-policy learning reduces empirical risk.

Algorithm minimizes regret in predictive models influenced by their own predictions.

Paper measures cognitive bias in positive feedback trading using diffusion process estimates.

We propose a model for the credit and liquidity risks faced by clearing members of Central Counterparty Clearing houses (CCPs). This model aims to capture the features of: gap risk; feedback between clearing member default, market volatility and margining requirements; the different risks faced by various types of mark…

We study an open problem of risk-sensitive portfolio allocation in a regime-switching credit market with default contagion. The state space of the Markovian regime-switching process is assumed to be a countably infinite set. To characterize the value function, we investigate the corresponding recursive infinite-dimensi…

Develops variational framework for LQG risk-sensitive MFGs with major-minor interactions.

Motivated by applications in clinical trials and finance, we study the problem of online convex optimization (with bandit feedback) where the decision maker is risk-averse. We provide two algorithms to solve this problem. The first one is a descent-type algorithm which is easy to implement. The second algorithm, which …

In machine learning we often try to optimise a decision rule that would have worked well over a historical dataset; this is the so called empirical risk minimisation principle. In the context of learning from recommender system logs, applying this principle becomes a problem because we do not have available the reward …

Feedback loops amplify dataset biases, affecting future model performance.

A general theory of innovation and progress in human society is outlined, based on the combat between two opposite forces (conservatism/inertia and speculative herding "bubble" behavior). We contend that human affairs are characterized by ubiquitous ``bubbles'', which involve huge risks which would not otherwise be tak…

We present a Bayesian view of counterfactual risk minimization (CRM) for offline learning from logged bandit feedback. Using PAC-Bayesian analysis, we derive a new generalization bound for the truncated inverse propensity score estimator. We apply the bound to a class of Bayesian policies, which motivates a novel, pote…

Adaptive reward models capture individual preferences from human feedback.

In this paper, we consider the asset-liability management under the mean-variance criterion. The financial market consists of a risk-free bond and a stock whose price process is modeled by a geometric Brownian motion. The liability of the investor is uncontrollable and is modeled by another geometric Brownian motion. W…

L-ARC improves model fairness by localizing risk guarantees.

We describe a simple model for speculative trading based on adaptive behavior of economic agents.The adaptive behavior is expressed through a feedback mechanism for changing agents' stock-to-bond ratios, depending on the past performance of their portfolios.The stock price is set according to the demand-supply for the …

A dealer manages quotes and rejection rules to control slippage risk in FX markets.

When we implement a portfolio selection methodology under a mean-risk formulation, it is essential to correctly model investors' risk aversion which may be time-dependent, or even state-dependent during the investment procedure. In this paper, we propose a behavior risk aversion model, which is a piecewise linear funct…

A new method uses counterfactual learning to improve recommendation system evaluation.

Adaptive sampler improves recommendation for implicit feedback data.

An assistant learns to mediate decisions between humans and experts, balancing risk and learning.

The paper proposes a method to align AI models using conformal risk control.

Modeling bank leverage dynamics to understand systemic risk in financial markets.

Develops a control framework for systemic risk under uncertainty.

Method improves volatility targeting for index construction.

We study a simple, solvable model that allows us to investigate effects of credit contagion on the default probability of individual firms, in both portfolios of firms and on an economy wide scale. While the effect of interactions may be small in typical (most probable) scenarios they are magnified, due to feedback, by…

New method detects currency contagion sources using causal inference.

The theory of convex risk functions has now been well established as the basis for identifying the families of risk functions that should be used in risk averse optimization problems. Despite its theoretical appeal, the implementation of a convex risk function remains difficult, as there is little guidance regarding ho…

Retraining stabilizes model influence on data.

Paper finds algorithms with both low regret and high exploitation.