arXiv subjects

Qi Deng

Publications and source records attributed to Qi Deng.

46 records · Page 3Linked to original sources

arXiv2023

The Impacts of Registration Regime Implementation on IPO Pricing Efficiency

We study the impacts of regime changes and related rule implementations on IPOs initial return for China entrepreneurial boards (ChiNext and STAR). We propose that an initial return contains the issuer fair value and an investors overreaction and examine their magnitudes and determinants. Our findings reveal an evolution of IPO pricing in response to the progression of regulation changes along four dimensions: 1) governing regulation regime, 2) listing day trading restrictions, 3) listing rules for issuers, and 4) participation requirements for investors. We find that the most efficient regulation regime in Chinese IPO pricing has four characteristics: 1) registration system, 2) no hard return caps nor trading curbs that restrict the initial return; 3) more specific listing rules for issuers, and 4) more stringent participation requirements for investors. In all contexts, we show that the registration regime governing the STAR IPOs offers the most efficient pricing.

q-fin.GN↗

arXiv2023

Stochastic Dimension-reduced Second-order Methods for Policy Optimization

In this paper, we propose several new stochastic second-order algorithms for policy optimization that only require gradient and Hessian-vector product in each iteration, making them computationally efficient and comparable to policy gradient methods. Specifically, we propose a dimension-reduced second-order method (DR-SOPO) which repeatedly solves a projected two-dimensional trust region subproblem. We show that DR-SOPO obtains an $\mathcal{O}(ε^{-3.5})$ complexity for reaching approximate first-order stationary condition and certain subspace second-order stationary condition. In addition, we present an enhanced algorithm (DVR-SOPO) which further improves the complexity to $\mathcal{O}(ε^{-3})$ based on the variance reduction technique. Preliminary experiments show that our proposed algorithms perform favorably compared with stochastic and variance-reduced policy gradient methods.

math.OC↗

arXiv2022

The Impact of Regulation Regime Changes on ChiNext IPOs: Effects of 2013 and 2020 Reforms on Pricing and Overreaction

Since its inauguration, ChiNext has gone through three time periods with two different regulation regimes and three different sets of listing day trading restrictions. This paper studies the impact of regulation regimes and listing day trading restrictions on the initial return of ChiNext IPOs. We hypothesize that the initial return of a ChiNext IPO contains the issuers intrinsic value and the investors overreaction. The intrinsic value is represented by the IPOs 21st day return (monthly return), and the difference between the monthly and initial returns (intramonth return) is a proxy of the overreaction. We find that all significant variables for all three returns in all three time periods fall into four categories: pre-listing demand, post-listing demand, market condition and pre-listing issuer value. We observe stark contrasts among variable categories for each of the returns in the three time periods, which reveals an evolution of the investors behavior with regard to the progression of regulation regimes. Based on our findings, we argue that the differences among the levels and determinants of initial return, monthly return (intrinsic value) and intramonth return (overreaction) in different time periods can be largely explained by regulation regime changes along two dimensions: 1) approval vs. registration and 2) listing day trading curbs and return limits. We find that IPO pricing is demand-driven under the approval regime, but value-driven under the registration regime. We further compare the impact of regulation regime changes on ChiNext IPO pricing practice, and propose a future research plan on ChiNext IPO pricing efficiency with policy implication.

q-fin.GN↗

arXiv2022

Stochastic First-order Methods for Convex and Nonconvex Functional Constrained Optimization

Functional constrained optimization is becoming more and more important in machine learning and operations research. Such problems have potential applications in risk-averse machine learning, semisupervised learning, and robust optimization among others. In this paper, we first present a novel Constraint Extrapolation (ConEx) method for solving convex functional constrained problems, which utilizes linear approximations of the constraint functions to define the extrapolation (or acceleration) step. We show that this method is a unified algorithm that achieves the best-known rate of convergence for solving different functional constrained convex composite problems, including convex or strongly convex, and smooth or nonsmooth problems with a stochastic objective and/or stochastic constraints. Many of these rates of convergence were in fact obtained for the first time in the literature. In addition, ConEx is a single-loop algorithm that does not involve any penalty subproblems. Contrary to existing primal-dual methods, it does not require the projection of Lagrangian multipliers into a (possibly unknown) bounded set. Second, for nonconvex functional constrained problems, we introduce a new proximal point method that transforms the initial nonconvex problem into a sequence of convex problems by adding quadratic terms to both the objective and constraints. Under a certain MFCQ-type assumption, we establish the convergence and rate of convergence of this method to KKT points when the convex subproblems are solved exactly or inexactly. For large-scale and stochastic problems, we present a more practical proximal point method in which the approximate solutions of the subproblems are computed by the aforementioned ConEx method. To the best of our knowledge, most of these convergence and complexity results of the proximal point method for nonconvex problems also seem to be new in the literature.

math.OC↗

arXiv2021

Minibatch and Momentum Model-based Methods for Stochastic Weakly Convex Optimization

Stochastic model-based methods have received increasing attention lately due to their appealing robustness to the stepsize selection and provable efficiency guarantee. We make two important extensions for improving model-based methods on stochastic weakly convex optimization. First, we propose new minibatch model-based methods by involving a set of samples to approximate the model function in each iteration. For the first time, we show that stochastic algorithms achieve linear speedup over the batch size even for non-smooth and non-convex (particularly, weakly convex) problems. To this end, we develop a novel sensitivity analysis of the proximal mapping involved in each algorithm iteration. Our analysis appears to be of independent interests in more general settings. Second, motivated by the success of momentum stochastic gradient descent, we propose a new stochastic extrapolated model-based method, greatly extending the classic Polyak momentum technique to a wider class of stochastic algorithms for weakly convex optimization. The rate of convergence to some natural stationarity condition is established over a fairly flexible range of extrapolation terms. While mainly focusing on weakly convex optimization, we also extend our work to convex optimization. We apply the minibatch and extrapolated model-based methods to stochastic convex optimization, for which we provide a new complexity bound and promising linear speedup in batch size. Moreover, an accelerated model-based method based on Nesterov's momentum is presented, for which we establish an optimal complexity bound for reaching optimality.

math.OC↗

arXiv2020

A Feasible Level Proximal Point Method for Nonconvex Sparse Constrained Optimization

Nonconvex sparse models have received significant attention in high-dimensional machine learning. In this paper, we study a new model consisting of a general convex or nonconvex objectives and a variety of continuous nonconvex sparsity-inducing constraints. For this constrained model, we propose a novel proximal point algorithm that solves a sequence of convex subproblems with gradually relaxed constraint levels. Each subproblem, having a proximal point objective and a convex surrogate constraint, can be efficiently solved based on a fast routine for projection onto the surrogate constraint. We establish the asymptotic convergence of the proposed algorithm to the Karush-Kuhn-Tucker (KKT) solutions. We also establish new convergence complexities to achieve an approximate KKT solution when the objective can be smooth/nonsmooth, deterministic/stochastic and convex/nonconvex with complexity that is on a par with gradient descent for unconstrained optimization problems in respective cases. To the best of our knowledge, this is the first study of the first-order methods with complexity guarantee for nonconvex sparse-constrained problems. We perform numerical experiments to demonstrate the effectiveness of our new model and efficiency of the proposed algorithm for large scale problems.

math.OC↗

arXiv2019

Artificial Intelligence BlockCloud (AIBC) Technical Whitepaper

The AIBC is an Artificial Intelligence and blockchain technology based large-scale decentralized ecosystem that allows system-wide low-cost sharing of computing and storage resources. The AIBC consists of four layers: a fundamental layer, a resource layer, an application layer, and an ecosystem layer. The AIBC implements a two-consensus scheme to enforce upper-layer economic policies and achieve fundamental layer performance and robustness: the DPoEV incentive consensus on the application and resource layers, and the DABFT distributed consensus on the fundamental layer. The DABFT uses deep learning techniques to predict and select the most suitable BFT algorithm in order to achieve the best balance of performance, robustness, and security. The DPoEV uses the knowledge map algorithm to accurately assess the economic value of digital assets.

cs.AI↗

arXiv2019

Efficiency of Coordinate Descent Methods For Structured Nonconvex Optimization

Novel coordinate descent (CD) methods are proposed for minimizing nonconvex functions consisting of three terms: (i) a continuously differentiable term, (ii) a simple convex term, and (iii) a concave and continuous term. First, by extending randomized CD to nonsmooth nonconvex settings, we develop a coordinate subgradient method that randomly updates block-coordinate variables by using block composite subgradient mapping. This method converges asymptotically to critical points with proven sublinear convergence rate for certain optimality measures. Second, we develop a randomly permuted CD method with two alternating steps: linearizing the concave part and cycling through variables. We prove asymptotic convergence to critical points and sublinear complexity rate for objectives with both smooth and concave parts. Third, we extend accelerated coordinate descent (ACD) to nonsmooth and nonconvex optimization to develop a novel randomized proximal DC algorithm whereby we solve the subproblem inexactly by ACD. Convergence is guaranteed with at most a few number of ACD iterations for each DC subproblem, and convergence complexity is established for identification of some approximate critical points. Fourth, we further develop the third method to minimize certain ill-conditioned nonconvex functions: weakly convex functions with high Lipschitz constant to negative curvature ratios. We show that, under specific criteria, the ACD-based randomized method has superior complexity compared to conventional gradient methods. Finally, an empirical study on sparsity-inducing learning models demonstrates that CD methods are superior to gradient-based methods for certain large-scale problems.

math.OC↗

arXiv2018

Optimal Adaptive and Accelerated Stochastic Gradient Descent

Stochastic gradient descent (\textsc{Sgd}) methods are the most powerful optimization tools in training machine learning and deep learning models. Moreover, acceleration (a.k.a. momentum) methods and diagonal scaling (a.k.a. adaptive gradient) methods are the two main techniques to improve the slow convergence of \textsc{Sgd}. While empirical studies have demonstrated potential advantages of combining these two techniques, it remains unknown whether these methods can achieve the optimal rate of convergence for stochastic optimization. In this paper, we present a new class of adaptive and accelerated stochastic gradient descent methods and show that they exhibit the optimal sampling and iteration complexity for stochastic optimization. More specifically, we show that diagonal scaling, initially designed to improve vanilla stochastic gradient, can be incorporated into accelerated stochastic gradient descent to achieve the optimal rate of convergence for smooth stochastic optimization. We also show that momentum, apart from being known to speed up the convergence rate of deterministic optimization, also provides us new ways of designing non-uniform and aggressive moving average schemes in stochastic optimization. Finally, we present some heuristics that help to implement adaptive accelerated stochastic gradient descent methods and to further improve their practical performance for machine learning and deep learning.

stat.ML↗

arXiv2015

Randomized Block Subgradient Methods for Convex Nonsmooth and Stochastic Optimization

Block coordinate descent methods and stochastic subgradient methods have been extensively studied in optimization and machine learning. By combining randomized block sampling with stochastic subgradient methods based on dual averaging, we present stochastic block dual averaging (SBDA)---a novel class of block subgradient methods for convex nonsmooth and stochastic optimization. SBDA requires only a block of subgradients and updates blocks of variables and hence has significantly lower iteration cost than traditional subgradient methods. We show that the SBDA-based methods exhibit the optimal convergence rate for convex nonsmooth stochastic optimization. More importantly, we introduce randomized stepsize rules and block sampling schemes that are adaptive to the block structures, which significantly improves the convergence rate w.r.t. the problem parameters. This is in sharp contrast to recent block subgradient methods applied to nonsmooth deterministic or stochastic optimization. For strongly convex objectives, we propose a new averaging scheme to make the regularized dual averaging method optimal, without having to resort to any accelerated schemes.

math.OC↗