arXiv subjects

Shang Liu

Publications and source records attributed to Shang Liu.

At least 73 records · Page 4Linked to original sources

arXiv2024

Understanding the Training and Generalization of Pretrained Transformer for Sequential Decision Making

In this paper, we consider the supervised pre-trained transformer for a class of sequential decision-making problems. The class of considered problems is a subset of the general formulation of reinforcement learning in that there is no transition probability matrix; though seemingly restrictive, the subset class of problems covers bandits, dynamic pricing, and newsvendor problems as special cases. Such a structure enables the use of optimal actions/decisions in the pre-training phase, and the usage also provides new insights for the training and generalization of the pre-trained transformer. We first note the training of the transformer model can be viewed as a performative prediction problem, and the existing methods and theories largely ignore or cannot resolve an out-of-distribution issue. We propose a natural solution that includes the transformer-generated action sequences in the training procedure, and it enjoys better properties both numerically and theoretically. The availability of the optimal actions in the considered tasks also allows us to analyze the properties of the pre-trained transformer as an algorithm and explains why it may lack exploration and how this can be automatically resolved. Numerically, we categorize the advantages of pre-trained transformers over the structured algorithms such as UCB and Thompson sampling into three cases: (i) it better utilizes the prior knowledge in the pre-training data; (ii) it can elegantly handle the misspecification issue suffered by the structured algorithms; (iii) for short time horizon such as $T\le50$, it behaves more greedy and enjoys much better regret than the structured algorithms designed for asymptotic optimality.

cs.LG↗

arXiv2024

VCD-Texture: Variance Alignment based 3D-2D Co-Denoising for Text-Guided Texturing

Recent research on texture synthesis for 3D shapes benefits a lot from dramatically developed 2D text-to-image diffusion models, including inpainting-based and optimization-based approaches. However, these methods ignore the modal gap between the 2D diffusion model and 3D objects, which primarily render 3D objects into 2D images and texture each image separately. In this paper, we revisit the texture synthesis and propose a Variance alignment based 3D-2D Collaborative Denoising framework, dubbed VCD-Texture, to address these issues. Formally, we first unify both 2D and 3D latent feature learning in diffusion self-attention modules with re-projected 3D attention receptive fields. Subsequently, the denoised multi-view 2D latent features are aggregated into 3D space and then rasterized back to formulate more consistent 2D predictions. However, the rasterization process suffers from an intractable variance bias, which is theoretically addressed by the proposed variance alignment, achieving high-fidelity texture synthesis. Moreover, we present an inpainting refinement to further improve the details with conflicting regions. Notably, there is not a publicly available benchmark to evaluate texture synthesis, which hinders its development. Thus we construct a new evaluation set built upon three open-source 3D datasets and propose to use four metrics to thoroughly validate the texturing performance. Comprehensive experiments demonstrate that VCD-Texture achieves superior performance against other counterparts.

cs.CV↗

arXiv2024

Efficient Preparation of Nonabelian Topological Orders in the Doubled Hilbert Space

Realizing nonabelian topological orders and their anyon excitations is an esteemed objective. In this work, we propose a novel approach towards this goal: quantum simulating topological orders in the doubled Hilbert space - the space of density matrices. We show that ground states of all quantum double models (toric code being the simplest example) can be efficiently prepared in the doubled Hilbert space; only finite-depth local operations are needed. In contrast, this is not the case in the conventional Hilbert space: Ground states of only some of these models are known to be efficiently preparable. Additionally, we find that nontrivial anyon braiding effects, both abelian and nonabelian, can be realized in the doubled Hilbert space, although the intrinsic nature of density matrices restricts possible excitations.

quant-ph↗

arXiv2024

Anyon Quantum Dimensions from an Arbitrary Ground State Wave Function

Realizing topological orders and topological quantum computation is a central task of modern physics. An important but notoriously hard question in this endeavor is how to diagnose topological orders that lack conventional order parameters. A breakthrough in this problem is the discovery of topological entanglement entropy, which can be used to detect nontrivial topological order from a ground state wave function, but is far from enough for fully determining the topological order. In this work, we take a key step further in this direction: We propose a simple entanglement-based protocol for extracting the quantum dimensions of all anyons from a single ground state wave function in two dimensions. The choice of the space manifold and the ground state is arbitrary. This protocol is both validated in the continuum and verified on lattices, and we anticipate it to be realizable in various quantum simulation platforms.

cond-mat.str-el↗

arXiv2024

Federated Graph Analytics with Differential Privacy

Collaborative graph analysis across multiple institutions is becoming increasingly popular. Realistic examples include social network analysis across various social platforms, financial transaction analysis across multiple banks, and analyzing the transmission of infectious diseases across multiple hospitals. We define the federated graph analytics, a new problem for collaborative graph analytics under differential privacy. Although differentially private graph analysis has been widely studied, it fails to achieve a good tradeoff between utility and privacy in federated scenarios, due to the limited view of local clients and overlapping information across multiple subgraphs. Motivated by this, we first propose a federated graph analytic framework, named FEAT, which enables arbitrary downstream common graph statistics while preserving individual privacy. Furthermore, we introduce an optimized framework based on our proposed degree-based partition algorithm, called FEAT+, which improves the overall utility by leveraging the true local subgraphs. Finally, extensive experiments demonstrate that our FEAT and FEAT+ significantly outperform the baseline approach by approximately one and four orders of magnitude, respectively.

cs.CR↗

arXiv2024

Towards Better Understanding of In-Context Learning Ability from In-Context Uncertainty Quantification

Predicting simple function classes has been widely used as a testbed for developing theory and understanding of the trained Transformer's in-context learning (ICL) ability. In this paper, we revisit the training of Transformers on linear regression tasks, and different from all the existing literature, we consider a bi-objective prediction task of predicting both the conditional expectation $\mathbb{E}[Y|X]$ and the conditional variance Var$(Y|X)$. This additional uncertainty quantification objective provides a handle to (i) better design out-of-distribution experiments to distinguish ICL from in-weight learning (IWL) and (ii) make a better separation between the algorithms with and without using the prior information of the training distribution. Theoretically, we show that the trained Transformer reaches near Bayes-optimum, suggesting the usage of the information of the training distribution. Our method can be extended to other cases. Specifically, with the Transformer's context window $S$, we prove a generalization bound of $\tilde{\mathcal{O}}(\sqrt{\min\{S, T\}/(n T)})$ on $n$ tasks with sequences of length $T$, providing sharper analysis compared to previous results of $\tilde{\mathcal{O}}(\sqrt{1/n})$. Empirically, we illustrate that while the trained Transformer behaves as the Bayes-optimal solution as a natural consequence of supervised training in distribution, it does not necessarily perform a Bayesian inference when facing task shifts, in contrast to the \textit{equivalence} between these two proposed in many existing literature. We also demonstrate the trained Transformer's ICL ability over covariates shift and prompt-length shift and interpret them as a generalization over a meta distribution.

cs.LG↗

arXiv2024

Annotating Slack Directly on Your Verilog: Fine-Grained RTL Timing Evaluation for Early Optimization

In digital IC design, compared with post-synthesis netlists or layouts, the early register-transfer level (RTL) stage offers greater optimization flexibility for both designers and EDA tools. However, timing information is typically unavailable at this early stage. Some recent machine learning (ML) solutions propose to predict the total negative slack (TNS) and worst negative slack (WNS) of an entire design at the RTL stage, but the fine-grained timing information of individual registers remains unavailable. In this work, we address the unique challenges of RTL timing prediction and introduce our solution named RTL-Timer. To the best of our knowledge, this is the first fine-grained general timing estimator applicable to any given design. RTL-Timer explores multiple promising RTL representations and proposes customized loss functions to capture the maximum arrival time at register endpoints. RTL-Timer's fine-grained predictions are further applied to guide optimization in a standard synthesis flow. The average results on unknown test designs demonstrate a correlation above 0.89, contributing around 3% WNS and 10% TNS improvement after optimization.

cs.AR↗

arXiv2024

When No-Rejection Learning is Consistent for Regression with Rejection

Learning with rejection has been a prototypical model for studying the human-AI interaction on prediction tasks. Upon the arrival of a sample instance, the model first uses a rejector to decide whether to accept and use the AI predictor to make a prediction or reject and defer the sample to humans. Learning such a model changes the structure of the original loss function and often results in undesirable non-convexity and inconsistency issues. For the classification with rejection problem, several works develop consistent surrogate losses for the joint learning of the predictor and the rejector, while there have been fewer works for the regression counterpart. This paper studies the regression with rejection (RwR) problem and investigates a no-rejection learning strategy that uses all the data to learn the predictor. We first establish the consistency for such a strategy under the weak realizability condition. Then for the case without the weak realizability, we show that the excessive risk can also be upper bounded with the sum of two parts: prediction error and calibration error. Lastly, we demonstrate the advantage of such a proposed learning strategy with empirical evidence.

cs.LG↗

arXiv2024

Towards Non-Invertible Anomalies from Generalized Ising Models

We present a general approach to the bulk-boundary correspondence of noninvertible topological phases, including both topological and fracton orders. This is achieved by a novel bulk construction protocol where solvable $(d+1)$-dimensional bulk models with noninvertible topology are constructed from the so-called generalized Ising (GI) models in $d$ dimensions. The GI models can then terminate on the boundaries of the bulk models. The construction generates abundant examples, including not only prototype ones such as $Z_2$ toric code models in any dimensions no less than two, and the X-cube fracton model, but also more diverse ones such as the $Z_2\times Z_2$ topological order, the 4d $Z_2$ topological order with pure-loop excitations, etc. The boundary of the solvable model is potentially anomalous and corresponds to precisely only sectors of the GI model that host certain total symmetry charges and/or satisfy certain boundary conditions. We derive a concrete condition for such bulk-boundary correspondence. The condition is violated only when the bulk model is either trivial or fracton ordered. A generalized notion of Kramers-Wannier duality plays an important role in the construction. Also, utilizing the duality, we find an example where a single anomalous theory can be realized on the boundaries of two distinct bulk fracton models, a phenomenon not expected in the case of topological orders. More generally, topological orders may also be generated starting with lattice models beyond the GI models, such as those with symmetry protected topological orders, through a variant bulk construction, which we provide in an appendix.

cond-mat.str-el↗

arXiv2023

CARGO: Crypto-Assisted Differentially Private Triangle Counting without Trusted Servers

Differentially private triangle counting in graphs is essential for analyzing connection patterns and calculating clustering coefficients while protecting sensitive individual information. Previous works have relied on either central or local models to enforce differential privacy. However, a significant utility gap exists between the central and local models of differentially private triangle counting, depending on whether or not a trusted server is needed. In particular, the central model provides a high accuracy but necessitates a trusted server. The local model does not require a trusted server but suffers from limited accuracy. Our paper introduces a crypto-assisted differentially private triangle counting system, named CARGO, leveraging cryptographic building blocks to improve the effectiveness of differentially private triangle counting without assumption of trusted servers. It achieves high utility similar to the central model but without the need for a trusted server like the local model. CARGO consists of three main components. First, we introduce a similarity-based projection method that reduces the global sensitivity while preserving more triangles via triangle homogeneity. Second, we present a triangle counting scheme based on the additive secret sharing that securely and accurately computes the triangles while protecting sensitive information. Third, we design a distributed perturbation algorithm that perturbs the triangle count with minimal but sufficient noise. We also provide a comprehensive theoretical and empirical analysis of our proposed methods. Extensive experiments demonstrate that our CARGO significantly outperforms the local model in terms of utility and achieves high-utility triangle counting comparable to the central model.

cs.CR↗

arXiv2023

MasterRTL: A Pre-Synthesis PPA Estimation Framework for Any RTL Design

In modern VLSI design flow, the register-transfer level (RTL) stage is a critical point, where designers define precise design behavior with hardware description languages (HDLs) like Verilog. Since the RTL design is in the format of HDL code, the standard way to evaluate its quality requires time-consuming subsequent synthesis steps with EDA tools. This time-consuming process significantly impedes design optimization at the early RTL stage. Despite the emergence of some recent ML-based solutions, they fail to maintain high accuracy for any given RTL design. In this work, we propose an innovative pre-synthesis PPA estimation framework named MasterRTL. It first converts the HDL code to a new bit-level design representation named the simple operator graph (SOG). By only adopting single-bit simple operators, this SOG proves to be a general representation that unifies different design types and styles. The SOG is also more similar to the target gate-level netlist, reducing the gap between RTL representation and netlist. In addition to the new SOG representation, MasterRTL proposes new ML methods for the RTL-stage modeling of timing, power, and area separately. Compared with state-of-the-art solutions, the experiment on a comprehensive dataset with 90 different designs shows accuracy improvement by 0.33, 0.22, and 0.15 in correlation for total negative slack (TNS), worst negative slack (WNS), and power, respectively.

cs.AR↗

arXiv2023

RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model

Inspired by the recent success of large language models (LLMs) like ChatGPT, researchers start to explore the adoption of LLMs for agile hardware design, such as generating design RTL based on natural-language instructions. However, in existing works, their target designs are all relatively simple and in a small scale, and proposed by the authors themselves, making a fair comparison among different LLM solutions challenging. In addition, many prior works only focus on the design correctness, without evaluating the design qualities of generated design RTL. In this work, we propose an open-source benchmark named RTLLM, for generating design RTL with natural language instructions. To systematically evaluate the auto-generated design RTL, we summarized three progressive goals, named syntax goal, functionality goal, and design quality goal. This benchmark can automatically provide a quantitative evaluation of any given LLM-based solution. Furthermore, we propose an easy-to-use yet surprisingly effective prompt engineering technique named self-planning, which proves to significantly boost the performance of GPT-3.5 in our proposed benchmark.

cs.LG↗

arXiv2023

Distribution-Free Model-Agnostic Regression Calibration via Nonparametric Methods

In this paper, we consider the uncertainty quantification problem for regression models. Specifically, we consider an individual calibration objective for characterizing the quantiles of the prediction model. While such an objective is well-motivated from downstream tasks such as newsvendor cost, the existing methods have been largely heuristic and lack of statistical guarantee in terms of individual calibration. We show via simple examples that the existing methods focusing on population-level calibration guarantees such as average calibration or sharpness can lead to harmful and unexpected results. We propose simple nonparametric calibration methods that are agnostic of the underlying prediction model and enjoy both computational efficiency and statistical consistency. Our approach enables a better understanding of the possibility of individual calibration, and we establish matching upper and lower bounds for the calibration error of our proposed methods. Technically, our analysis combines the nonparametric analysis with a covering number argument for parametric analysis, which advances the existing theoretical analyses in the literature of nonparametric density estimation and quantile bandit problems. Importantly, the nonparametric perspective sheds new theoretical insights into regression calibration in terms of the curse of dimensionality and reconciles the existing results on the impossibility of individual calibration. To our knowledge, we make the first effort to reach both individual calibration and finite-sample guarantee with minimal assumptions in terms of conformal prediction. Numerical experiments show the advantage of such a simple approach under various metrics, and also under covariates shift. We hope our work provides a simple benchmark and a starting point of theoretical ground for future research on regression calibration.

cs.LG↗

arXiv2023

UnifiedSSR: A Unified Framework of Sequential Search and Recommendation

In this work, we propose a Unified framework of Sequential Search and Recommendation (UnifiedSSR) for joint learning of user behavior history in both search and recommendation scenarios. Specifically, we consider user-interacted products in the recommendation scenario, user-interacted products and user-issued queries in the search scenario as three distinct types of user behaviors. We propose a dual-branch network to encode the pair of interacted product history and issued query history in the search scenario in parallel. This allows for cross-scenario modeling by deactivating the query branch for the recommendation scenario. Through the parameter sharing between dual branches, as well as between product branches in two scenarios, we incorporate cross-view and cross-scenario associations of user behaviors, providing a comprehensive understanding of user behavior patterns. To further enhance user behavior modeling by capturing the underlying dynamic intent, an Intent-oriented Session Modeling module is designed for inferring intent-oriented semantic sessions from the contextual information in behavior sequences. In particular, we consider self-supervised learning signals from two perspectives for intent-oriented semantic session locating, which encourage session discrimination within each behavior sequence and session alignment between dual behavior sequences. Extensive experiments on three public datasets demonstrate that UnifiedSSR consistently outperforms state-of-the-art methods for both search and recommendation.

cs.IR↗

arXiv2023

Mixed-State Entanglement Measures in Topological Order

Quantum entanglement is a particularly useful characterization of topological orders which lack conventional order parameters. In this work, we study the entanglement in topologically ordered states between two arbitrary spatial regions, using two distinct mixed-state entanglement measures: the so-called "computable cross-norm or realignment" (CCNR) negativity, and the more well-known partial-transpose (PT) negativity. We first generally compute the entanglement measures: We obtain general expressions both in (2+1)D Chern-Simons field theories under certain simplifying conditions, and in the Pauli stabilizer formalism that applies to lattice models in all dimensions. While the field-theoretic results are expected to be topological and universal, the lattice results contain nontopological/nonuniversal terms as well. This raises the important problem of continuum-lattice comparison which is crucial for practical applications. When the two spatial regions and the remaining subsystem do not have triple intersection, we solve the problem by proposing a general strategy for extracting the topological and universal terms in both entanglement measures. Examples in the (2+1)D $Z_2$ toric code model are also presented. In the presence of trisection points, however, our result suggests that the subleading piece in the PT negativity is not topological and depends on the local geometry of the trisections, which is in harmonics with a technical subtlety in the field-theoretic calculation.

cond-mat.str-el↗

arXiv2023

Maximum Optimality Margin: A Unified Approach for Contextual Linear Programming and Inverse Linear Programming

In this paper, we study the predict-then-optimize problem where the output of a machine learning prediction task is used as the input of some downstream optimization problem, say, the objective coefficient vector of a linear program. The problem is also known as predictive analytics or contextual linear programming. The existing approaches largely suffer from either (i) optimization intractability (a non-convex objective function)/statistical inefficiency (a suboptimal generalization bound) or (ii) requiring strong condition(s) such as no constraint or loss calibration. We develop a new approach to the problem called \textit{maximum optimality margin} which designs the machine learning loss function by the optimality condition of the downstream optimization. The max-margin formulation enjoys both computational efficiency and good theoretical properties for the learning procedure. More importantly, our new approach only needs the observations of the optimal solution in the training data rather than the objective function, which makes it a new and natural approach to the inverse linear programming problem under both contextual and context-free settings; we also analyze the proposed method under both offline and online settings, and demonstrate its performance using numerical experiments.

cs.LG↗

arXiv2023

A Crypto-Assisted Approach for Publishing Graph Statistics with Node Local Differential Privacy

Publishing graph statistics under node differential privacy has attracted much attention since it provides a stronger privacy guarantee than edge differential privacy. Existing works related to node differential privacy assume a trusted data curator who holds the whole graph. However, in many applications, a trusted curator is usually not available due to privacy and security issues. In this paper, for the first time, we investigate the problem of publishing the graph degree distribution under Node Local Differential privacy (Node-LDP), which does not rely on a trusted server. We propose an algorithm to publish the degree distribution with Node-LDP by exploring how to select the optimal graph projection parameter and how to execute the local graph projection. Specifically, we propose a Crypto-assisted local projection method that combines LDP and cryptographic primitives, achieving higher accuracy than our baseline PureLDP local projection method. On the other hand, we improve our baseline Node-level parameter selection by proposing an Edge-level parameter selection that preserves more neighboring information and provides better utility. Finally, extensive experiments on real-world graphs show that Edge-level local projection provides higher accuracy than Node-level local projection, and Crypto-assisted parameter selection owns the better utility than PureLDP parameter selection, improving by up to 79.8% and 57.2% respectively.

cs.CR↗

arXiv2022

Bounding Entanglement Entropy Using Zeros of Local Correlation Matrices

Correlation functions and entanglement are two different aspects to characterize quantum many-body states. While many correlation functions are experimentally accessible, entanglement entropy (EE), the simplest characterization of quantum entanglement, is usually difficult to measure. In this Letter, we propose a protocol to bound EE by local measurements. This protocol utilizes local correlation matrices and focuses on their (approximate) zero eigenvalues. Given a quantum state, each (approximate) zero eigenvalue can be used to define a set of local projection operators. An auxiliary Hamiltonian can then be constructed by summing these projectors. When the construction only involves projectors of zero eigenvalues, we prove the EE of a subsystem is bounded by the ground-state degeneracy of the auxiliary Hamiltonian on this subsystem. When projectors from nonzero eigenvalues are included, we show the EE can be bounded by a thermal entropy of the subsystem. Our protocol can be applied experimentally to investigate exotic quantum many-body states prepared in quantum simulators.

cond-mat.str-el↗