Point cloud completion aims to reconstruct complete 3D shapes from partial observations, which is a challenging problem due to severe occlusions and missing geometry. Despite recent advances in multimodal techniques that leverage complementary RGB images to compensate for missing geometry, most methods still follow a Completion-by-Inpainting paradigm, synthesizing missing structures from fused latent features. We empirically show that this paradigm often results in structural inconsistencies and topological artifacts due to limited geometric and semantic constraints. To address this, we rethink the task and propose a more robust paradigm, termed Completion-by-Correction, which begins with a topologically complete shape prior generated by a pretrained image-to-3D model and performs feature-space correction to align it with the partial observation. This paradigm shifts completion from unconstrained synthesis to guided refinement, enabling structurally consistent and observation-aligned reconstruction. Building upon this paradigm, we introduce PGNet, a multi-stage framework that conducts dual-feature encoding to ground the generative prior, synthesizes a coarse yet structurally aligned scaffold, and progressively refines geometric details via hierarchical correction. Experiments on the ShapeNetViPC dataset demonstrate the superiority of PGNet over state-of-the-art baselines in terms of average Chamfer Distance (-23.5%) and F-score (+7.1%).

The ever-growing end user data demands, and the reductions in memory costs are fueling edge-caching deployments. Caching at the edge is substantially different from that at the core and needs to consider the nature of individualized data demands. For example, an individual user may not be interested in requesting the same data item again, if it has recently requested it. Such individualized dynamics are not apparent in the aggregated data requests at the core and have not been considered in popularity-driven caching designs for the core. Hence, these traditional caching policies could induce significant inefficiencies when applied at the edges. To address this issue, we develop new edge caching policies optimized for the individualized demands that also leverage overhearing opportunities at the wireless edge. With the objective of maximizing the hit ratio, the proposed policies will actively evict the data items that are not likely to be requested in the near future, and strategically bring them back into the cache via overhearing when they become popular again. Both theoretical analysis and numerical simulations demonstrate that the proposed edge caching policies could outperform the popularity-driven policies that are optimal at the core.

Edge caching has been widely implemented to efficiently serve data requests from end users. Numerous edge caching policies have been proposed to adaptively update the cache contents based on various statistics. One critical statistic is the miss cost, which could measure the latency or the bandwidth/energy consumption to resolve the cache miss. Existing caching policies typically assume that the miss cost for each data item is fixed and known. However, in real systems, they could be random with unknown statistics. A promising approach would be to use online learning to estimate the unknown statistics of these random costs, and make caching decisions adaptively. Unfortunately, conventional learning techniques cannot be directly applied, because the caching problem has additional cache capacity and cache update constraints that are not covered in traditional learning settings. In this work, we resolve these issues by developing a novel edge caching policy that learns uncertain miss costs efficiently, and is shown to be asymptotically optimal. We first derive an asymptotic lower bound on the achievable regret. We then design a Kullback-Leibler lower confidence bound (KL-LCB) based edge caching policy, which adaptively learns the random miss costs by following the “optimism in the face of uncertainty” principle. By employing a novel analysis that accounts for the new constraints and the dynamics of the setting, we prove that the regret of the proposed policy matches the regret lower bound, thus showing asymptotic optimality. Further, via numerical experiments we demonstrate the performance improvements of our policy over natural benchmarks.

Edge caching has been widely implemented to efficiently serve data requests from end users. Numerous edge caching policies have been proposed to adaptively update cache content based on various statistics including data popularities and miss costs. Nevertheless, these policies typically assume that the miss cost for each data item is known, which is not true in real systems. A promising approach would be to use online learning to estimate these unknown miss costs. However, existing techniques cannot be directly applied, because the caching problem has additional cache capacity and cache update constraints that are not covered in traditional learning settings. In this work, we resolve these issues by developing a novel edge caching policy that learns uncertainty miss costs efficiently, and is shown to be asymptotically optimal. We first derive an asymptotic lower bound on the achievable regret. We then design a Kullback-Leibler lower confidence bound (KL-LCB) based edge caching policy, which adaptively learns the random miss costs by following the “optimism in the face of uncertainty” principle. By employing a novel analysis that accounts for the new constraints and the dynamics of the setting, we prove that the regret of the proposed policy matches the regret lower bound, thus showing asymptotic optimality. Further, via numerical experiments we demonstrate the performance improvements of our policy over natural benchmarks.

Least-recently-used (LRU) caching and its variants have conventionally been used as a fundamental and critical method to ensure fast and efficient data access in computer and communication systems. Emerging data-intensive applications over unreliable channels, e.g., mobile edge computing and wireless content delivery networks, have imposed new challenges in optimizing LRU caching in environments prone to failures. Most existing studies focus on reliable channels, e.g., on wired Web servers and within data centers, which have already yielded good insights and successful algorithms. Surprisingly, we show that these insights do not necessarily hold true for unreliable channels. We consider a single-hop multi-cache distributed system with data items being dispatched by random hashing. The objective is to design efficient cache organization and data placement that minimize the miss probability. The former allocates the total memory space to each of the involved caches. The latter decides data routing and replication strategies. Analytically, we characterize the asymptotic miss probabilities for unreliable LRU caches, and optimize the system design. Remarkably, these results sometimes are counterintuitive, differing from the ones obtained for reliable caches. We discover an interesting phenomenon: allocating the cache space unequally can achieve a better performance, even when channel reliability levels are equal. In addition, we prove that splitting the total cache space into separate LRU caches can achieve a lower asymptotic miss probability than organizing the total space in a single LRU cache. These results provide new and even counterintuitive insights that motivate novel designs for caching systems over unreliable channels.

Least-recently-used (LRU) caching and its variants have conventionally been used as a fundamental and critical method to ensure fast and efficient data access in computer and communication systems. Emerging data-intensive applications over unreliable channels, e.g., mobile edge computing and wireless content delivery networks, have imposed new challenges in optimizing LRU caching systems in environments prone to failures. Most existing studies focus on reliable channels, e.g., on wired Web servers and within data centers, which have already yielded good insights with successful algorithms on how to reduce cache miss ratios. Surprisingly, we show that these widely held insights do not necessarily hold true for unreliable channels. We consider a single-hop multi-cache distributed system with data items being dispatched by random hashing. The objective is to achieve efficient cache organization and data placement. The former allocates the total memory space to each of the involved caches. The latter decides data routing strategies and data replication schemes. Analytically we characterize the unreliable LRU caches by explicitly deriving their asymptotic miss probabilities. Based on these results, we optimize the system design. Remarkably, these results sometimes are counterintuitive, differing from the ones obtained for reliable caches. We discover an interesting phenomenon: asymmetric cache organization is optimal even for symmetric channels. Specifically, even when channel unreliability probabilities are equal, allocating the cache spaces unequally can achieve a better performance. We also propose an explicit unequal allocation policy that outperforms the equal allocation. In addition, we prove that splitting the total cache space into separate LRU caches can achieve a lower asymptotic miss probability than resource pooling that organizes the total space in a single LRU cache. These results provide new and even counterintuitive insights that motivate novel designs for caching systems over unreliable channels. They can potentially be exploited to further improve the system performance in real practice.

To efficiently scale data caching infrastructure to support emerging big data applications, many caching systems rely on consistent hashing to group a large number of servers to form a cooperative cluster. These servers are organized together according to a random hash function. They jointly provide a unified but distributed hash table to serve swift and voluminous data item requests. Different from the single least-recently-used (LRU) server that has already been extensively studied, theoretically characterizing a cluster that consists of multiple LRU servers remains yet to be explored. These servers are not simply added together; the random hashing complicates the behavior. To this end, we derive the asymptotic miss ratio of data item requests on a LRU cluster with consistent hashing. We show that these individual cache spaces on different servers can be effectively viewed as if they could be pooled together to form a single virtual LRU cache space parametrized by an appropriate cache size. This equivalence can be established rigorously under the condition that the cache sizes of the individual servers are large. For typical data caching systems this condition is common. Our theoretical framework provides a convenient abstraction that can directly apply the results from the simpler single LRU cache to the more complex LRU cluster with consistent hashing.

Least-recently-used (LRU) caching systems have been widely used, and are increasingly deployed driven by emerging trends for big data. In a typical scenario, these systems are used to serve multiple flows of dependent data item requests that are also correlated over time. These flows compete for the limited cache space. Characterizing the miss ratios of these competing flows can facilitate the design and improve the system performance. The existing asymptotic analyses for correlated requests give explicit results for Zipf's distributions with the index greater than a critical value (one). Consequently, the asymptotic result is inaccurate around this critical point, which notably is also the typical parameter region reported by many empirical measurements. In contrast, we derive the asymptotic miss ratios of multiple flows for a large class of truncated heavy-tailed data item popularity distributions with time dependency. Importantly, it significantly improves the accuracy in numerical computations when the index of a Zipf's distribution is close to one. Moreover, the result generalizes beyond Zipf's distributions, e.g., to Weibull, for multiple flows of correlated data item requests. Our asymptotic result directly exploits the critical properties of the distribution and the truncated support region. As our versatile expression is explicit, it avoids the numerical computations required by the characteristic time approximation. Interestingly, it also validates the characteristic time approximation with new forms for multiple flows of competing requests that are correlated over time under certain conditions.