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.
This work broadens calibeating to various proper losses using Bregman divergence.
This work generalizes calibeating for a broader range of proper losses using Bregman divergence.
New risk measure considers horizon risk and interest rate uncertainty.
New loss functions based on f-divergences improve language model performance.
This paper develops sparse alternatives to continuous distributions, including new types of Gaussians and attention mechanisms.
The paper studies convergence rates of Tsallis entropic regularization in optimal transport.
This paper studies Fenchel-Young losses, a generic way to construct convex loss functions from a regularization function. We analyze their properties in depth, showing that they unify many well-known loss functions and allow to create useful new ones easily. Fenchel-Young losses constructed from a generalized entropy, …
Improves policy optimization with polylog(T) regret bounds for stochastic losses.
Gradient descent converges with arbitrary stepsize for separable data under Fenchel-Young losses.
In this paper, we present a new class of Markov decision processes (MDPs), called Tsallis MDPs, with Tsallis entropy maximization, which generalizes existing maximum entropy reinforcement learning (RL). A Tsallis MDP provides a unified framework for the original RL problem and RL with various types of entropy, includin…
Simplified proof for Tsallis-INF algorithm without conjugate functions.
We develop a variant of multiclass logistic regression that is significantly more robust to noise. The algorithm has one weight vector per class and the surrogate loss is a function of the linear activations (one per class). The surrogate loss of an example with linear activation vector and class has t…
Modified Bakry-Émery criterion inequality for Tsallis entropy monotonicity.
Paper finds a new principle for optimizing consumption and wealth using Tsallis entropy.
The construction of efficient and effective decision trees remains a key topic in machine learning because of their simplicity and flexibility. A lot of heuristic algorithms have been proposed to construct near-optimal decision trees. ID3, C4.5 and CART are classical decision tree algorithms and the split criteria they…
We derive an algorithm that achieves the optimal (within constants) pseudo-regret in both adversarial and stochastic multi-armed bandits without prior knowledge of the regime and time horizon. The algorithm is based on online mirror descent (OMD) with Tsallis entropy regularization with power and reduced-varian…
This is full length article (draft version) where problem number of topics in Topic Modeling is discussed. We proposed idea that Renyi and Tsallis entropy can be used for identification of optimal number in large textual collections. We also report results of numerical experiments of Semantic stability for 4 topic mode…
We introduce a temperature into the exponential function and replace the softmax output layer of neural nets by a high temperature generalization. Similarly, the logarithm in the log loss we use for training is replaced by a low temperature logarithm. By tuning the two temperatures we create loss functions that are non…
In this study, we analyze the aerospace stocks prices in order to characterize the sector behavior. The data analyzed cover the period from January 1987 to April 1999. We present a new index for the aerospace sector and we investigate the statistical characteristics of this index. Our results show that this index is we…
We proposed the agent-based model of financial markets where agents (or traders) are represented by three-state spins located on the plane lattice or social network. The spin variable represents only the individual opinion (advice) that each trader gives to his nearest neighbors. In the model the agents can be consider…
Develops a Best-of-Both-Worlds algorithm for linear contextual bandits with Tsallis entropy.
Estimate relaxation times in nonextensive systems using gradient flow for Tsallis entropy maximization.
Optimal control in latent factor models uses Tsallis entropy for exploration.
A hybrid impurity measure balances theoretical soundness and computational efficiency.
Improved regret bounds for Tsallis-INF in adversarial bandits and corruptions.
The paper sets lower bounds for adversarial robustness in multiclass classification.
This paper introduces a new potential function using Tsallis entropy for neural network optimization.
Coupled entropy corrects flaws in Tsallis entropy for complex systems.
This study uses Tsallis entropy to analyze diversification and integration in Italian stock market companies.
Study analyzes stock market dynamics using Tsallis statistics and GHE, revealing pre-bubble and post-bubble market characteristics.
Paper presents characteristic function of Tsallis q-Gaussian and its applications.
In this paper, we propose a novel maximum causal Tsallis entropy (MCTE) framework for imitation learning which can efficiently learn a sparse multi-modal policy distribution from demonstrations. We provide the full mathematical analysis of the proposed framework. First, the optimal solution of an MCTE problem is shown …
We find the wealth distribution for an economic agent in the financial market, in analogy with standard derivation of generaliz Boltzman (Tsallis) factor in statistical mechanics. In this respect, Tsallis entropic index separates two different regimes, the large and small size market. The Pareto like wealth distributio…
Study on utility maximization with Tsallis entropy in reinforcement learning.
Earlier studies have shown that stock market distributions can be well described by distributions derived from Tsallis entropy, which is a generalization of Shannon entropy to non-extensive systems. In this paper, Tsallis relative entropy (TRE), which is the generalization of Kullback-Leibler relative entropy (KLRE) to…
The paper calculates bounds for risk metrics and entropies under partial information constraints.
This work models financial market returns with asymmetric Tsallis distributions, improving fit over symmetric q-Gaussians.
We developed a strategic of optimal portfolio based on information theory and Tsallis statistics. The growth rate of a stock market is defined by using -deformed functions and we find that the wealth after n days with the optimal portfolio is given by a -exponential function. In this context, the asymptotic optim…
A pricing principle is introduced for non-attainable claims in incomplete markets.
New method uses asymmetric Tsallis relative entropy for better risk assessment in financial portfolios.
We recently showed that the S&P500 stock market index is well described by Tsallis non-extensive statistics and nonlinear Fokker-Planck time evolution. We argued that these results should be applicable to a broad range of markets and exchanges where anomalous diffusion and `heavy' tails of the distribution are present.…
The theoretical basis for a candidate variational principle for the information bottleneck (IB) method is formulated within the ambit of the generalized nonadditive statistics of Tsallis. Given a nonadditivity parameter , the role of the \textit{additive duality} of nonadditive statistics () in relating…
Recently deep reinforcement learning (DRL) has achieved outstanding success on solving many difficult and large-scale RL problems. However the high sample cost required for effective learning often makes DRL unaffordable in resource-limited applications. With the aim of improving sample efficiency and learning performa…
In this paper we study the possible microscopic origin of heavy-tailed probability density distributions for the price variation of financial instruments. We extend the standard log-normal process to include another random component in the so-called stochastic volatility models. We study these models under an assumptio…
Sparse RSP routing improves graph exploration and classification.
One of the major issues studied in finance that has always intrigued, both scholars and practitioners, and to which no unified theory has yet been discovered, is the reason why prices move over time. Since there are several well-known traditional techniques in the literature to measure stock market volatility, a centra…
Near-optimal per-action regret bounds for sleeping bandits are derived.
Distributions derived from non-extensive Tsallis statistics are closely connected with dynamics described by a nonlinear Fokker-Planck equation. The combination shows promise in describing stochastic processes with power-law distributions and superdiffusive dynamics. We investigate intra-day price changes in the S&P500…