Author name cluster

Siqi Wu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2025 Conference Paper

Conditional Latent Coding with Learnable Synthesized Reference for Deep Image Compression

Siqi Wu
Yinda Chen
Dong Liu
Zhihai He

In this paper, we study how to synthesize a dynamic reference from an external dictionary to perform conditional coding of the input image in the latent domain and how to learn the conditional latent synthesis and coding modules in an end-to-end manner. Our approach begins by constructing a universal image feature dictionary using a multi-stage approach involving modified spatial pyramid pooling, dimension reduction, and multi-scale feature clustering. For each input image, we learn to synthesize a conditioning latent by selecting and synthesizing relevant features from the dictionary, which significantly enhances the model's capability in capturing and exploring image source correlation. This conditional latent synthesis involves a correlation-based feature matching and alignment strategy, comprising a Conditional Latent Matching (CLM) module and a Conditional Latent Synthesis (CLS) module. The synthesized latent is then used to guide the encoding process, allowing for more efficient compression by exploiting the correlation between the input image and the reference dictionary. According to our theoretical analysis, the proposed conditional latent coding (CLC) method is robust to perturbations in the external dictionary samples and the selected conditioning latent, with an error bound that scales logarithmically with the dictionary size, ensuring stability even with large and diverse dictionaries. Experimental results on benchmark datasets show that our new method improves the coding performance by a large margin (up to 1.2 dB) with a very small overhead of approximately 0.5% bits per pixel.

PDF Details DOI

EAAI Journal 2023 Journal Article

Exploring 2-rank strategic weight manipulation in multiple attribute decision making and its applications in project review and university ranking

Yating Liu
Siqi Wu
Congcong Li
Yucheng Dong

In some real multiple attribute decision making (MADM) problems, sometimes, it is time-consuming and unnecessary to obtain a complete ranking of alternatives, thus, a decision maker would classify the alternatives into two ordered categories, forming a 2-rank MADM problem. Occasionally, a decision maker can manipulate the desired 2-rank results by strategically setting attribute weights. This process is called 2-rank strategic weight manipulation (2RSWM). First, this study defines the 2-rank range of alternatives. Subsequently, several mixed 0–1 linear programming models (MLPMs) are constructed to obtain the 2-rank range and the strategic attribute weight vector of the desired 2-rank result of the alternative(s) of the decision maker. Furthermore, we provide conditions for the existence of the strategic attribute weight vector based on the 2-rank range of the alternatives and the proposed MLPMs. Finally, two illustrative examples and two simulation experiments are conducted to validate the effectiveness of our proposed models. Due to the ordered weighted averaging (OWA) operator having smaller average width of the 2-rank range, and a larger minimum distance between the impersonal and strategic attribute weight vectors, we argue that the OWA operator has a better performance than the weighted averaging (WA) operator in defending against 2RSWM.

Details DOI

ICAPS Conference 2023 Conference Paper

Sensitivity Analysis for Dynamic Control of PSTNs with Skewed Distributions

Rosy Chen
Yiran Ma
Siqi Wu
James C. Boerkoel Jr.

Probabilistic Simple Temporal Networks (PSTN) facilitate solving many interesting scheduling problems by characterizing uncertain task durations with unbounded probabilistic distributions. However, most current approaches assess PSTN performance using normal or uniform distributions of temporal uncertainty. This paper explores how well such approaches extend to families of non-symmetric distributions shown to better represent the temporal uncertainty introduced by, e. g. , human teammates by building new PSTN benchmarks. We also build probability-aware variations of current approaches that are more reactive to the shape of the underlying distributions. We empirically evaluate the original and modified approaches over well-established PSTN datasets. Our results demonstrate that alignment between the planning model and reality significantly impacts performance. While our ideas for augmenting existing algorithms to better account for human-style uncertainty yield only marginal gains, our results surprisingly demonstrate that existing methods handle positively-skewed temporal uncertainty better.

Details

JMLR Journal 2020 Journal Article

Unique Sharp Local Minimum in L1-minimization Complete Dictionary Learning

Yu Wang
Siqi Wu
Bin Yu

We study the problem of globally recovering a dictionary from a set of signals via $\ell_1$-minimization. We assume that the signals are generated as i.i.d. random linear combinations of the $K$ atoms from a complete reference dictionary $D^*\in \mathbb R^{K\times K}$, where the linear combination coefficients are from either a Bernoulli type model or exact sparse model. First, we obtain a necessary and sufficient norm condition for the reference dictionary $D^*$ to be a sharp local minimum of the expected $\ell_1$ objective function. Our result substantially extends that of Wu and Yu (2015) and allows the combination coefficient to be non-negative. Secondly, we obtain an explicit bound on the region within which the objective value of the reference dictionary is minimal. Thirdly, we show that the reference dictionary is the unique sharp local minimum, thus establishing the first known global property of $\ell_1$-minimization dictionary learning. Motivated by the theoretical results, we introduce a perturbation based test to determine whether a dictionary is a sharp local minimum of the objective function. In addition, we also propose a new dictionary learning algorithm based on Block Coordinate Descent, called DL-BCD, which is guaranteed to decrease the obective function monotonically. Simulation studies show that DL-BCD has competitive performance in terms of recovery rate compared to other state-of-the-art dictionary learning algorithms when the reference dictionary is generated from random Gaussian matrices. [abs] [ pdf ][ bib ] &copy JMLR 2020. ( edit, beta )

PDF Details

JMLR Journal 2018 Journal Article

Local Identifiability of $\ell_1$-minimization Dictionary Learning: a Sufficient and Almost Necessary Condition

Siqi Wu
Bin Yu

We study the theoretical properties of learning a dictionary from $N$ signals $\mathbf{x}_i\in \mathbb R^K$ for $i=1,\ldots,N$ via $\ell_1$-minimization. We assume that $\mathbf{x}_i$'s are $i.i.d.$ random linear combinations of the $K$ columns from a complete (i.e., square and invertible) reference dictionary $\mathbf{D}_0 \in \mathbb R^{K\times K}$. Here, the random linear coefficients are generated from either the $s$-sparse Gaussian model or the Bernoulli-Gaussian model. First, for the population case, we establish a sufficient and almost necessary condition for the reference dictionary $\mathbf{D}_0$ to be locally identifiable, i.e., a strict local minimum of the expected $\ell_1$-norm objective function. Our condition covers both sparse and dense cases of the random linear coefficients and significantly improves the sufficient condition by Gribonval and Schnass (2010). In addition, we show that for a complete $\mu$-coherent reference dictionary, i.e., a dictionary with absolute pairwise column inner-product at most $\mu\in[0,1)$, local identifiability holds even when the random linear coefficient vector has up to $O(\mu^{-2})$ nonzero entries. Moreover, our local identifiability results also translate to the finite sample case with high probability provided that the number of signals $N$ scales as $O(K\log K)$. [abs] [ pdf ][ bib ] &copy JMLR 2018. ( edit, beta )

PDF Details